Semantic segmentation takes a pivotal role in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in advance. In this paper, we construct an automatic data generation pipeline Gen4Seg to stress-test semantic segmentation models by generating various challenging samples with different attribute changes. Beyond previous evaluation paradigms focusing solely on global weather and style transfer, we investigate variations in both appearance and geometry attributes at the object and image level. These include object color, material, size, and position, as well as image-level variations such as weather and style. To achieve this, we propose to edit visual attributes of existing real images with precise control of structural information, empowered by diffusion models. In this way, the existing segmentation labels can be reused for the edited images, which greatly reduces the labor costs of constructing datasets. Using our pipeline, we construct two new benchmarks, Pascal-EA and COCO-EA. We benchmark a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models. We have several key findings: 1) advanced open-vocabulary models do not exhibit greater robustness compared to closed-set methods under geometric variations; 2) traditional data augmentation techniques, such as CutOut and CutMix, are limited in enhancing robustness against appearance variations; 3) our generation pipeline can also be employed as a data augmentation tool and improve both in-distribution and out-of-distribution performances. Our work suggests the potential of generative models as effective tools for automatically analyzing segmentation models, and we hope our findings will assist practitioners and researchers in developing more robust and reliable segmentation models.

The development of Text-to-Video (T2V) generation has made motion transfer possible, enabling the control of video motion based on existing footage. However, current methods have two limitations: 1) struggle to handle multi-subjects videos, failing to transfer specific subject motion; 2) struggle to preserve the diversity and accuracy of motion as transferring to subjects with varying shapes. To overcome these, we introduce ConMo, a zero-shot framework that disentangle and recompose the motions of subjects and camera movements. ConMo isolates individual subject and background motion cues from complex trajectories in source videos using only subject masks, and reassembles them for target video generation. This approach enables more accurate motion control across diverse subjects and improves performance in multi-subject scenarios. Additionally, we propose soft guidance in the recomposition stage which controls the retention of original motion to adjust shape constraints, aiding subject shape adaptation and semantic transformation. Unlike previous methods, ConMo unlocks a wide range of applications, including subject size and position editing, subject removal, semantic modifications, and camera motion simulation. Extensive experiments demonstrate that ConMo significantly outperforms state-of-the-art methods in motion fidelity and semantic consistency. The code is available at https://github.com/Andyplus1/ConMo.

In daily clinical practice, clinicians exhibit robustness in identifying polyps with both location and size variations. It is uncertain if deep segmentation models can achieve comparable robustness in automated colonoscopic analysis. To benchmark the model robustness, we focus on evaluating the segmentation models on the polyps with various attributes (e.g. location and size) and healthy samples. Based on the Latent Diffusion Model, we perform attribute editing on real polyps and build a new dataset named Polyp-E. Our synthetic dataset boasts exceptional realism, to the extent that clinical experts find it challenging to discern them from real data. We evaluate various existing polyp segmentation models on the proposed benchmark. The results reveal most of the models are highly sensitive to attribute variations. As a novel data augmentation technique, the proposed editing pipeline can improve both in-distribution and out-ofdistribution generalization ability. The code and datasets has been released at https://github.com/RunpuWei/Polyp-E-Benchmark.

When deploying segmentation models in practice, it is critical to evaluate their behaviors in varied and complex scenes. Different from the previous evaluation paradigms only in consideration of global attribute variations (e.g. adverse weather), we investigate both local and global attribute variations for robustness evaluation. To achieve this, we construct a mask-preserved attribute editing pipeline to edit visual attributes of real images with precise control of structural information. Therefore, the original segmentation labels can be reused for the edited images. Using our pipeline, we construct a benchmark covering both object and image attributes (e.g. color, material, pattern, style). We evaluate a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models on their robustness to different types of variations. We find that both local and global attribute variations affect segmentation performances, and the sensitivity of models diverges across different variation types. We argue that local attributes have the same importance as global attributes, and should be considered in the robustness evaluation of segmentation models. Code: https://github.com/PRIS-CV/Pascal-EA.

Abstract Deep learning has achieved great success in academic benchmarks but fails to work effectively in the real world due to the potential dataset bias. The current learning methods are prone to inheriting or even amplifying the bias present in a training dataset and under-represent specific demographic groups. More recently, some dataset debiasing methods have been developed to address the above challenges based on the awareness of protected or sensitive attribute labels. However, the number of protected or sensitive attributes may be considerably large, making it laborious and costly to acquire sufficient manual annotation. To this end, we propose a prototype-based network to dynamically balance the learning of different subgroups for a given dataset. First, an object pattern embedding mechanism is presented to make the network focus on the foreground region. Then we design a prototype learning method to discover and extract the visual patterns from the training data in an unsupervised way. The number of prototypes is dynamic depending on the pattern structure of the feature space. We evaluate the proposed prototype-based network on three widely used polyp segmentation datasets with abundant qualitative and quantitative experiments. Experimental results show that our proposed method outperforms the CNN-based and transformer-based state-of-the-art methods in terms of both effectiveness and fairness metrics. Moreover, extensive ablation studies are conducted to show the effectiveness of each proposed component and various parameter values. Lastly, we analyze how the number of prototypes grows during the training process and visualize the associated subgroups for each learned prototype. The code and data will be released at https://github.com/zijinY/dynamic-prototype-debiasing .

Polyp segmentation is important in the early diagnosis and treatment of colorectal cancer. Since polyps vary in shape, size, color, and texture, accurate polyp segmentation is very challenging. One promising solution is to model the contextual relation for each pixel. However, previous methods only focus on learning the dependencies between the position within an individual image and ignore the contextual relation across different images. In this paper, we propose a memory-based feature enhancement module to capture the cross-image contextual relations. Specifically, we first present a polyp-centric representation. Then a semantic memory is designed to extract the polyp prototypes across different images. The feature at one position can be further enhanced by the contextual embeddings stored in the semantic memory. The enhanced feature is propagated into the features of the previous levels as the multi-scale guidance. The experimental results show that our method achieves better performance than other state-of-the-art methods.

Action repetition counting is to estimate the occurrence times of the repetitive motion in one action, which is a relatively new, significant, but challenging problem. To solve this problem, we propose a new method superior to the traditional ways in two aspects, without preprocessing and applicable for arbitrary periodicity actions. Without preprocessing, the proposed model makes our scheme convenient for real applications; processing the arbitrary periodicity action makes our model more suitable for the actual circumstance. In terms of methodology, firstly, we extract action features using ConvNets and then use Principal Component Analysis algorithm to generate the intuitive periodic information from the chaotic high-dimensional features; secondly, we propose an energy-based adaptive feature mode selection scheme to adaptively select proper deep feature mode according to the background of the video; thirdly,we construct the periodic waveform of the action based on the high-energy rules by filtering the irrelevant information. Finally, we detect the peaks to obtain the times of the action repetition. Our work features two-fold: 1) We give a significant insight that features extracted by ConvNets for action recognition can well model the self-similarity periodicity of the repetitive action. 2) A high-energy based periodicity mining rule using features from ConvNets is presented, which can process arbitrary actions without preprocessing. Experimental results show that our method achieves superior or comparable performance on the three benchmark datasets, i.e. YT_Segments, QUVA, and RARV.