This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of relying on explicit motion alignment, such as optical flow warping, we propose a novel knowledge distillation schema coined as Delta Distillation. In our proposal, the student learns the variations in the teacher’s intermediate features over time. We demonstrate that these temporal variations can be effectively distilled due to the temporal redundancies within video frames. During inference, both teacher and student cooperate for providing predictions: the former by providing initial representations extracted only on the key-frame, and the latter by iteratively estimating and applying deltas for the successive frames. Moreover, we consider various design choices to learn optimal student architectures including an end-to-end learnable architecture search. By extensive experiments on a wide range of architectures, including the most efficient ones, we demonstrate that delta distillation sets a new state of the art in terms of accuracy vs. efficiency tradeoff for semantic segmentation and object detection in videos. Finally, we show that, as a by-product, delta distillation improves the temporal consistency of the teacher model.
论文检索
输入标题、作者或关键词，从 5,999 篇学术成果中精准定位
Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation
PDF ↗This paper introduces a unified framework for video action segmentation via sequence to sequence (seq2seq) translation in a fully and timestamp supervised setup. In contrast to current state-of-the-art frame-level prediction methods, we view action segmentation as a seq2seq translation task, i.e., mapping a sequence of video frames to a sequence of action segments. Our proposed method involves a series of modifications and auxiliary loss functions on the standard Transformer seq2seq translation model to cope with long input sequences opposed to short output sequences and relatively few videos. We incorporate an auxiliary supervision signal for the encoder via a frame-wise loss and propose a separate alignment decoder for an implicit duration prediction. Finally, we extend our framework to the timestamp supervised setting via our proposed constrained k-medoids algorithm to generate pseudo-segmentations. Our proposed framework performs consistently on both fully and timestamp supervised settings, outperforming or competing state-of-the-art on several datasets.
We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur). Precise spotting requires models to reason globally about the full-time scale of actions and locally to identify subtle frame-to-frame appearance and motion differences that identify events during these actions. Surprisingly, we find that top performing solutions to prior video understanding tasks such as action detection and segmentation do not simultaneously meet both requirements. In response, we propose E2E-Spot, a compact, end-to-end model that performs well on the precise spotting task and can be trained quickly on a single GPU. We demonstrate that E2E-Spot significantly outperforms recent baselines adapted from the video action detection, segmentation, and spotting literature to the precise spotting task. Finally, we contribute new annotations and splits to several fine-grained sports action datasets to make these datasets suitable for future work on precise spotting.
We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely labelled, and a large collection of videos are unlabelled. To this end, we propose two novel loss functions for the unlabelled data: an action affinity loss and an action continuity loss. The action affinity loss guides the unlabelled samples learning by imposing the action priors induced from the labelled set. Action continuity loss enforces the temporal continuity of actions, which also provides frame-wise classification supervision. In addition, we propose an Adaptive Boundary Smoothing (ABS) approach to build coarser action boundaries for more robust and reliable learning. The proposed loss functions and ABS were evaluated on three benchmarks. Results show that they significantly improved action segmentation performance with a low amount (5% and 10%) of labelled data and achieved comparable results to full supervision with 50% labelled data. Furthermore, ABS succeeded in boosting performance when integrated into fully-supervised learning.
Current methods for video activity localisation over time assume implicitly that activity temporal boundaries labelled for model training are determined and precise. However, in unscripted natural videos, different activities mostly transit smoothly, so that it is intrinsically ambiguous to determine in labelling precisely when an activity starts and ends over time. Such uncertainties in temporal labelling are currently ignored in model training, resulting in learning mis-matched video-text correlation with poor generalisation in test. In this work, we solve this problem by introducing Elastic Moment Bounding (EMB) to accommodate flexible and adaptive activity temporal boundaries towards modelling universally interpretable video-text correlation with tolerance to underlying temporal uncertainties in pre-fixed annotations. Specifically, we construct elastic boundaries adaptively by mining and discovering frame-wise temporal endpoints that can maximise the alignment between video segments and query sentences. To enable both more accurate matching (segment content attention) and more robust localisation (segment elastic boundaries), we optimise the selection of frame-wise endpoints subject to segment-wise contents by a novel Guided Attention mechanism. Extensive experiments on three video activity localisation benchmarks demonstrate compellingly the EMB’s advantages over existing methods without modelling uncertainty.
The Audio-Visual Event Localization (AVEL) problem involves tackling three core sub-tasks: the creation of efficient audio-visual representations using cross-modal guidance, the formation of short-term temporal feature aggregations, and its accumulation to achieve long-term dependency resolution. These sub-tasks are often performed by tailored modules, where the limited inter-module interaction restricts feature learning to a serialized manner. Past works have traditionally viewed videos as temporally sequenced multi-modal streams. We improve and extend on this view by proposing a novel architecture, the Dual Perspective Network (DPNet), that - (1) additionally operates on an intuitive graph perspective of a video to simultaneously facilitate cross-modal guidance and short-term temporal aggregation using a Graph NeuralNetwork (GNN), (2) deploys a Temporal Convolutional Network (TCN)to achieve long-term dependency resolution, and (3) encourages interactive feature learning using an acyclic feature refinement process that alternates between the GNN and TCN. Further, we introduce the RelationalGraph Convolutional Transformer, a novel GNN integrated into the DP-Net, to express and attend each segment node’s relational representation with its different relational neighborhoods. Lastly, we diversify the input to the DPNet through a new video augmentation technique called Replicate and Link, which outputs semantically identical video blends whose graph representations can be linked to that of the source videos. Experiments reveal that our DPNet framework outperforms prior state-of-the-art methods by large margins for the AVEL task on the public AVE dataset, while extensive ablation studies corroborate the efficacy of each proposed method.
Autonomous highlight detection is crucial for video editing and video browsing on social media platforms. General video highlight detection aims at extracting the most interesting segments from the entire video. However, interest is subjective among different users. A naive solution is to train a model for each user but it is not practical due to the huge training expense. In this work, we propose a Preference-Adaptive Classification (PAC-Net) framework, which can model users’ personalized preferences from their user history. Specifically, we design a Decision Boundary Customizer (DBC) module to dynamically generate the user-adaptive highlight classifier from the preference-related user history. In addition, we introduce the Mini-History (Mi-Hi) mechanism to capture more fine-grained user-specific preferences. The final highlight prediction is jointly decided by the user’s multiple preferences. Extensive experiments demonstrate that the proposed PAC-Net achieves state-of-the-art performance on the public benchmark dataset, whilst using substantially smaller networks. Code will be made publicly available.
Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS). Most of the previous methods directly extract and fuse the motion and appearance features for segmenting target objects in the UVOS setting. However, optical flow is intrinsically an instantaneous velocity of all pixels among consecutive frames, thus making the motion features not aligned well with the primary objects among the corresponding frames. To solve the above challenge, we propose a concise, practical, and efficient architecture for appearance and motion feature alignment, dubbed hierarchical feature alignment network (HFAN). Specifically, the key merits in HFAN are the sequential Feature AlignMent (FAM) module and the Feature AdaptaTion (FAT) module, which are leveraged for processing the appearance and motion features hierarchically. FAM is capable of aligning both appearance and motion features with the primary object semantic representations, respectively. Further, FAT is explicitly designed for the adaptive fusion of appearance and motion features to achieve a desirable trade-off between cross-modal features. Extensive experiments demonstrate the effectiveness of the proposed HFAN, which reaches a new state-of-the-art performance on DAVIS-16, achieving 88.7 J&F Mean, i.e., a relative improvement of 3.5% over the best published result.
Action anticipation involves predicting future actions having observed the initial portion of a video. Typically, the observed video is processed as a whole to obtain a video-level representation of the ongoing activity in the video, which is then used for future prediction. We introduce ANTICIPATR which performs long-term action anticipation leveraging segment-level representations learned using individual segments from different activities, in addition to a video-level representation. We propose a two-stage learning approach to train a novel transformer-based model that uses these two types of representations to directly predict a set of future action instances over any given anticipation duration. Results on Breakfast, 50Salads, Epic-Kitchens-55, and EGTEA Gaze+ datasets demonstrate the effectiveness of our approach.
YouTube users looking for instructions for a specific task may spend a long time browsing content trying to find the right video that matches their needs. Creating a visual summary (abridged version of a video) provides viewers with a quick overview and massively reduces search time. In this work, we focus on summarizing instructional videos, an under-explored area of video summarization. In comparison to generic videos, instructional videos can be parsed into semantically meaningful segments that correspond to important steps of the demonstrated task. Existing video summarization datasets rely on manual frame-level annotations, making them subjective and limited in size. To overcome this, we first automatically generate pseudo summaries for a corpus of instructional videos by exploiting two key assumptions: (i) relevant steps are likely to appear in multiple videos of the same task (Task Relevance), and (ii) they are more likely to be described by the demonstrator verbally (Cross-Modal Saliency). We propose an instructional video summarization network that combines a context-aware temporal video encoder and a segment scoring transformer. Using pseudo summaries as weak supervision, our network constructs a visual summary for an instructional video given only video and transcribed speech. To evaluate our model, we collect a high-quality test set, WikiHow Summaries, by scraping WikiHow articles that contain video demonstrations and visual depictions of steps allowing us to obtain the ground-truth summaries. We outperform several baselines and a state-of-the-art video summarization model on this new benchmark.
The essence of video semantic segmentation (VSS) is how to leverage temporal information for prediction. Previous efforts are mainly devoted to developing new techniques to calculate the cross-frame affinities such as optical flow and attention. Instead, this paper contributes from a different angle by mining relations among cross-frame affinities, upon which better temporal information aggregation could be achieved. We explore relations among affinities in two aspects: single-scale intrinsic correlations and multi-scale relations. Inspired by traditional feature processing, we propose Single-scale Affinity Refinement (SAR) and Multi-scale Affinity Aggregation (MAA). To make it feasible to execute MAA, we propose a Selective Token Masking (STM) strategy to select a subset of consistent reference tokens for different scales when calculating affinities, which also improves the efficiency of our method. At last, the cross-frame affinities strengthened by SAR and MAA are adopted for adaptively aggregating temporal information. Our experiments demonstrate that the proposed method performs favorably against state-of-the-art VSS methods.
The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially true as the level of details in spatio-temporal video understanding and with it, the complexity of annotations continues to increase. Rather than performing few-shot learning with a human oracle to provide a few densely labelled support videos, we propose to automatically learn to find appropriate support videos given a query. We call this self-shot learning and we outline a simple self-supervised learning method to generate an embedding space well-suited for unsupervised retrieval of relevant samples. To showcase this novel setting, we tackle, for the first time, video instance segmentation in a self-shot (and few-shot) setting, where the goal is to segment instances at the pixel-level across the spatial and temporal domains. We provide strong baseline performances that utilize a novel transformer-based model and show that self-shot learning can even surpass few-shot and can be positively combined for further performance gains. Experiments on new benchmarks show that our approach achieves strong performance, is competitive to oracle support in some settings, scales to large unlabelled video collections, and can be combined in a semi-supervised setting.
This paper focuses on the weakly-supervised audio-visual video parsing task, which aims to recognize all events belonging to each modality and localize their temporal boundaries. This task is challenging because only overall labels indicating the video events are provided for training. However, an event might be labeled but not appear in one of the modalities, which results in a modality-specific noisy label problem. In this work, we propose a training strategy to identify and remove modality-specific noisy labels dynamically. It is motivated by two key observations: 1) networks tend to learn clean samples first; and 2) a labeled event would appear in at least one modality. Specifically, we sort the losses of all instances within a mini-batch individually in each modality, and then select noisy samples according to the relationships between intra-modal and inter-modal losses. Besides, we also propose a simple but valid noise ratio estimation method by calculating the proportion of instances whose confidence is below a preset threshold. Our method makes large improvements over the previous state of the arts (\eg, from 60.0\% to 63.8\% in segment-level visual metric), which demonstrates the effectiveness of our approach. Code and trained models are publicly available at \url{https://github.com/MCG-NJU/JoMoLD}.
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these challenges since they feature a much higher dynamic range and are resilient to motion blur. Nonetheless, semantic segmentation with event cameras is still in its infancy which is chiefly due to the lack of high-quality, labeled datasets. In this work, we introduce ESS (Event-based Semantic Segmentation), which tackles this problem by directly transferring the semantic segmentation task from existing labeled image datasets to unlabeled events via unsupervised domain adaptation (UDA). Compared to existing UDA methods, our approach aligns recurrent, motion-invariant event embeddings with image embeddings. For this reason, our method neither requires video data nor per-pixel alignment between images and events and, crucially, does not need to hallucinate motion from still images. Additionally, we introduce DSEC-Semantic, the first large-scale event-based dataset with fine-grained labels. We show that using image labels alone, ESS outperforms existing UDA approaches, and when combined with event labels, it even outperforms state-of-the-art supervised approaches on both DDD17 and DSEC-Semantic. Finally, ESS is general-purpose, which unlocks the vast amount of existing labeled image datasets and paves the way for new and exciting research directions in new fields previously inaccessible for event cameras.
Transferability metrics is a maturing field with increasing interest, which aims at providing heuristics for selecting the most suitable source models to transfer to a given target dataset, without fine-tuning them all. However, existing works rely on custom experimental setups which differ across papers, leading to inconsistent conclusions about which transferability metrics work best. In this paper we conduct a large-scale study by systematically constructing a broad range of 715k experimental setup variations. We discover that even small variations to an experimental setup lead to different conclusions about the superiority of a transferability metric over another. Then we propose better evaluations by aggregating across many experiments, enabling to reach more stable conclusions. As a result, we reveal the superiority of LogME at selecting good source datasets to transfer from in a semantic segmentation scenario, NLEEP at selecting good source architectures in an image classification scenario, and GBC at determining which target task benefits most from a given source model. Yet, no single transferability metric works best in all scenarios.
ML-BPM: Multi-Teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation
PDF ↗Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains. The goal of OCDA is to minimize the domain gap between the source domain and the compound target domain, which brings the benefit of the model generalization to the unseen domains. Current OCDA for semantic segmentation methods adopt manual domain separation and employ a single model to adapt to all the target subdomains simultaneously. However, adapting to a target subdomain hinders the model from adapting to other dissimilar target subdomains, which leads to limited performance. In this work, we introduce a multi-teacher framework with bidirectional photometric mixing to adapt to every target subdomain separately. First, we present an automatic domain separation to find the optimal number of subdomains. On this basis, we propose a multi-teacher framework in which each teacher model uses the bidirectional photometric mixing to adapt to one target subdomain. Furthermore, we conduct an adaptive distillation to learn a student model and apply consistency regularization to improve the student generalization. Experimental results on benchmark datasets demonstrate the effectiveness of our approach for both the compound domain and the open domains against existing state-of-the-art approaches.
Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops in accuracy and offline adaptation may not be enough to contrast it. In this paper, we tackle Online Domain Adaptation (OnDA) for semantic segmentation. We design a pipeline that is robust to continuous domain shifts, either gradual or sudden, and we evaluate it in the case of rainy and foggy scenarios. Our experiments show that our framework can effectively adapt to new domains during deployment, while not being affected by catastrophic forgetting of the previous domains.
Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In practice, new images are usually made available in a consecutive manner, leading to a problem called Continual Semantic Segmentation (CSS). Typically, CSS faces the forgetting problem since previous training images are unavailable, and the semantic shift problem of the background class. Considering the semantic segmentation as a context-dependent pixel-level classification task, we explore CSS from a new perspective of context analysis in this paper. We observe that the context of old-class pixels in the new images is much more biased on new classes than that in the old images, which can sharply aggravate the old-class forgetting and new-class overfitting. To tackle the obstacle, we propose a biased-context-rectified CSS framework with a context-rectified image-duplet learning scheme and a biased-context-insensitive consistency loss. Furthermore, we propose an adaptive re-weighting class-balanced learning strategy for the biased class distribution. Our approach outperforms state-of-the-art methods by a large margin in existing CSS scenarios.
Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient contrastive learning method for unsupervised domain adaptive semantic segmentation. Previous domain adaptation methods merely consider the alignment of the intra-class representational distributions across various domains, while the inter-class structural relationship is insufficiently explored, resulting in the aligned representations on the target domain might not be as easily discriminated as done on the source domain anymore. Instead, ProCA incorporates inter-class information into class-wise prototypes, and adopts the class-centered distribution alignment for adaptation. By considering the same class prototypes as positives and other class prototypes as negatives to achieve class-centered distribution alignment, ProCA achieves state-of-the-art performance on classical domain adaptation tasks, {\em i.e., GTA5 $\to$ Cityscapes \text{and} SYNTHIA $\to$ Cityscapes}. Code will be made available.
Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings assume no domain change in the output space. In semantic prediction tasks, different datasets are often labeled according to different semantic taxonomies. In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain. We therefore introduce the more general taxonomy adaptive cross-domain semantic segmentation (TACS) problem, allowing for inconsistent taxonomies between the two domains. We further propose an approach that jointly addresses the image-level and label-level domain adaptation. On the label-level, we employ a bilateral mixed sampling strategy to augment the target domain, and a relabelling method to unify and align the label spaces. We address the image-level domain gap by proposing an uncertainty-rectified contrastive learning method, leading to more domain-invariant and class-discriminative features. We extensively evaluate the effectiveness of our framework under different TACS settings: open taxonomy, coarse-to-fine taxonomy, and implicitly-overlapping taxonomy. Our approach outperforms the previous state-of-the-art by a large margin, while being capable of adapting to target taxonomies. Our implementation is publicly available at https://github.com/ETHRuiGong/TADA.