United States

Existing semantic segmentation works have been mainly focused on designing effective decoders; however, the computational load introduced by the overall structure has long been ignored, which hinders their applications on resource-constrained hardwares. In this paper, we propose a head-free lightweight architecture specifically for semantic segmentation, named Adaptive Frequency Transformer (AFFormer). AFFormer adopts a parallel architecture to leverage prototype representations as specific learnable local descriptions which replaces the decoder and preserves the rich image semantics on high-resolution features. Although removing the decoder compresses most of the computation, the accuracy of the parallel structure is still limited by low computational resources. Therefore, we employ heterogeneous operators (CNN and vision Transformer) for pixel embedding and prototype representations to further save computational costs. Moreover, it is very difficult to linearize the complexity of the vision Transformer from the perspective of spatial domain. Due to the fact that semantic segmentation is very sensitive to frequency information, we construct a lightweight prototype learning block with adaptive frequency filter of complexity $O(n)$ to replace standard self attention with $O(n^{2})$. Extensive experiments on widely adopted datasets demonstrate that AFFormer achieves superior accuracy while retaining only 3M parameters. On the ADE20K dataset, AFFormer achieves 41.8 mIoU and 4.6 GFLOPs, which is 4.4 mIoU higher than Segformer, with  45% less GFLOPs. On the Cityscapes dataset, AFFormer achieves 78.7 mIoU and 34.4 GFLOPs, which is 2.5 mIoU higher than Segformer with 72.5% less GFLOPs.

AAAI 2023

Head-Free Lightweight Semantic Segmentation with Linear Transformer

cv: scene analysis & understanding

cv: applications

cv: segmentation

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Quantification (or prevalence estimation) algorithms aim at predicting the class distribution of unseen sets (or bags) of examples. These methods are useful for two main tasks: 1) quantification applications, for instance when we need to track the proportions of several groups of interest over time, and 2) domain adaptation problems, in which we usually need to adapt a previously trained classifier to a different --albeit related-- target distribution according to the estimated prevalences. This paper analyzes several binary quantification algorithms showing that not only do they share a common framework but are, in fact, equivalent. Inspired by this study, we propose a new method that extends one of the approaches analyzed. After an empirical evaluation of all these methods using synthetic and benchmark datasets, the paper concludes recommending three of them due to their precision, efficiency, and diversity.

An Equivalence Analysis of Binary Quantification Methods

Multi-instance learning (MIL) is a supervised learning where each example is a labeled bag with many instances. The typical MIL strategies are to train an instance-level feature extractor followed by aggregating instances features as bag-level representation with labeled information. However, learning such a bag-level representation highly depends on a large number of labeled datasets, which are difficult to get in real-world scenarios. In this paper, we make the first attempt to propose a robust Self-supervised Multi-Instance LEarning architecture with Structure awareness (SMILEs) that learns unsupervised bag representation. Our proposed approach is: 1) permutation invariant to the order of instances in bag; 2) structure-aware to encode the topological structures among the instances; and 3) robust against instances noise or permutation. Specifically, to yield robust MIL model without label information, we augment the multi-instance bag and train the representation encoder to maximize the correspondence between the representations of the same bag in its different augmented forms. Moreover, to capture topological structures from nearby instances in bags, our framework learns optimal graph structures for the bags and these graphs are optimized together with message passing layers and the ordered weighted averaging operator towards contrastive loss. Our main theorem characterizes the permutation invariance of the bag representation. Compared with state-of-the-art supervised MIL baselines, SMILEs achieves average improvement of 4.9%, 4.4% in classification accuracy on 5 benchmark datasets and 20 newsgroups datasets, respectively. In addition, we show that the model is robust to the input corruption.

Robust Self-supervised Multi-instance Learning with Structure Awareness

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often conceptually complicated. This paper proposes a novel and highly effective QAT method, quantized feature distillation (QFD). QFD first trains a quantized (or binarized) representation as the teacher, then quantize the network using knowledge distillation (KD). Quantitative results show that QFD is more flexible and effective (i.e., quantization friendly) than previous quantization methods. QFD surpasses existing methods by a noticeable margin on not only image classification but also object detection, albeit being much simpler. Furthermore, QFD quantizes ViT and Swin-Transformer on MS-COCO detection and segmentation, which verifies its potential in real world deployment. To the best of our knowledge, this is the first time that vision transformers have been quantized in object detection and image segmentation tasks.

Quantized Feature Distillation for Network Quantization

Real-time video perception tasks are often challenging over the resource-constrained edge devices due to the concerns of accuracy drop and hardware overhead, where saving computations is the key to performance improvement. Existing methods either rely on domain-specific neural chips or priorly searched models, which require specialized optimization according to different task properties. In this work, we propose a general and task-independent Patch Automatic Skip Scheme (PASS), a novel end-to-end learning pipeline to support diverse video perception settings by decoupling acceleration and tasks. The gist is to capture the temporal similarity across video frames and skip the redundant computations at patch level, where patch is a non-overlapping square block in visual. PASS equips each convolution layer with a learnable gate to selectively determine which patches could be safely skipped without degrading model accuracy. As to each layer, a desired gate needs to make flexible skip decisions based on intermediate features without any annotations, which cannot be achieved by conventional supervised learning paradigm. To address this challenge, we are the first to construct a tough self-supervisory procedure for optimizing these gates, which learns to extract contrastive representation, i.e., distinguishing similarity and difference, from frame sequence. These high-capacity gates can serve as a plug-and-play module for convolutional neural network (CNN) backbones to implement patch-skippable architectures, and automatically generate proper skip strategy to accelerate different video-based downstream tasks, e.g., outperforming the state-of-the-art MobileHumanPose (MHP) in 3D pose estimation and FairMOT in multiple object tracking, by up to 9.43 times and 12.19 times speedups, respectively. By directly processing the raw data of frames, PASS can generalize to real-time video streams on commodity edge devices, e.g., NVIDIA Jetson Nano and mobile phones, and achieves efficient performance in realistic deployment.

PASS: Patch Automatic Skip Scheme for Efficient Real-time Video Perception on Edge Devices

Mirror detection aims to identify the mirror regions in the given input image. Existing works mainly focus on integrating the semantic features and structural features to mine specific relations between mirror and non-mirror regions, or introducing mirror properties like depth or chirality to help analyze the existence of mirrors. In this work, we observe that a real object typically forms a loose symmetry relationship with its corresponding reflection in the mirror, which is beneficial in distinguishing mirrors from real objects. Based on this observation, we propose a dual-path Symmetry-Aware Transformer-based mirror detection Network (SATNet), which includes two novel modules: Symmetry-Aware Attention Module (SAAM) and Contrast and Fusion Decoder Module (CFDM). Specifically, we first adopt a transformer backbone to model global information aggregation in images, extracting multi-scale features in two paths. We then feed the high-level dual-path features to SAAMs to capture the symmetry relations. Finally, we fuse the dual-path features and refine our prediction maps progressively with CFDMs to obtain the final mirror mask. Experimental results show that SATNet outperforms both RGB and RGB-D mirror detection methods on all available mirror detection datasets.

Symmetry-Aware Transformer-based Mirror Detection

Deep operator network (DeepONet) has demonstrated great
success in various learning tasks, including learning solution
operators of partial differential equations. In particular, it provides
 an efficient approach to predicting the evolution equations
in a finite time horizon. Nevertheless, the vanilla DeepONet
suffers from the issue of stability degradation in the long-
time prediction. This paper proposes a transfer-learning aided
DeepONet to enhance the stability. Our idea is to use transfer
learning to sequentially update the DeepONets as the surro-
gates for propagators learned in different time frames. The
evolving DeepONets can better track the varying complexities
of the evolution equations, while only need to be updated by
efficient training of a tiny fraction of the operator networks.
Through systematic experiments, we show that the proposed
method not only improves the long-time accuracy of Deep-
ONet while maintaining similar computational cost but also
substantially reduces the sample size of the training set.

Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations

In combinatorial causal bandits (CCB), the learning agent chooses at most $K$ variables in each round to intervene, collects feedback from the observed variables, with the goal of minimizing expected regret on the target variable $Y$. We study under the context of binary generalized linear models (BGLMs) with a succinct parametric representation of the causal models. We present the algorithm BGLM-OFU for Markovian BGLMs (i.e. no hidden variables) based on the maximum likelihood estimation method, and show that it achieves $O(\sqrt{T}\log T)$ regret, where $T$ is the time horizon. For the special case of linear models with hidden variables, we apply causal inference techniques such as the do calculus to convert the original model into a Markovian model, and then show that our BGLM-OFU algorithm and another algorithm based on the linear regression both solve such linear models with hidden variables. Our novelty includes (a) considering the combinatorial intervention action space and the general causal models including ones with hidden variables, (b) integrating and adapting techniques from diverse studies such as generalized linear bandits and online influence maximization, and (c) avoiding unrealistic assumptions (such as knowing the joint distribution of the parents of $Y$ under all interventions) and regret factors exponential to causal graph size in prior studies.

Combinatorial Causal Bandits

Just noticeable difference (JND) refers to the maximum visual change that human eyes cannot perceive, and it has a wide range of applications in multimedia systems. However, most existing JND approaches only focus on a single modality, and rarely consider the complementary effects of multimodal information. In this article, we investigate the JND modeling from an end-to-end homologous multimodal perspective, namely hmJND-Net. Specifically, we explore three important visually sensitive modalities, including saliency, depth, and segmentation. To better utilize homologous multimodal information, we establish an effective fusion method via summation enhancement and subtractive offset, and align homologous multimodal features based on a self-attention driven encoder-decoder paradigm. Extensive experimental results on eight different benchmark datasets validate the superiority of our hmJND-Net over eight representative methods.

Just Noticeable Visual Redundancy Forecasting: A Deep Multimodal-driven Approach

Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news. We conjecture that such issues result from representing entities as static embeddings of superficial words, while neglecting to model their ever-changing states, i.e., the information they carry, as the text unfolds. Therefore, we extend the Transformer model to dynamically conduct entity state updates and sentence realization for narrative generation. We propose a contrastive framework to learn the state representations in a discrete space, and insert additional attention layers into the decoder to better exploit these states. Experiments on two narrative datasets show that our model can generate more coherent and diverse narratives than strong baselines with the guidance of meaningful entity states.

Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework

Survival prediction based on whole slide images (WSIs) is a challenging task for patient-level multiple instance learning (MIL). Due to the vast amount of data for a patient (one or multiple gigapixels WSIs) and the irregularly shaped property of WSI, it is difficult to fully explore spatial, contextual, and hierarchical interaction in the patient-level bag. Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag. In this work, we propose a hierarchical vision Transformer framework named HVTSurv, which can encode the local-level relative spatial information, strengthen WSI-level context-aware communication, and establish patient-level hierarchical interaction. Firstly, we design a feature pre-processing strategy, including feature rearrangement and random window masking. Then, we devise three layers to progressively obtain patient-level representation, including a local-level interaction layer adopting Manhattan distance, a WSI-level interaction layer employing spatial shuffle, and a patient-level interaction layer using attention pooling. Moreover, the design of hierarchical network helps the model become more computationally efficient. Finally, we validate HVTSurv with 3,104 patients and 3,752 WSIs across 6 cancer types from The Cancer Genome Atlas (TCGA). The average C-Index is  2.50-11.30% higher than all the prior weakly supervised methods over 6 TCGA datasets. Ablation study and attention visualization further verify the superiority of the proposed HVTSurv. Implementation is available at: https://github.com/szc19990412/HVTSurv.

Downloads

Next from AAAI 2023

An Equivalence Analysis of Binary Quantification Methods

Similar lecture

FeedFormer: Revisiting Transformer Decoder for Efficient Semantic Segmentation