Yutong Dai

Le Xue, Manli Shu, Anas Awadalla et al. · salesforce, stanford

This paper introduces BLIP-3, an open framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. We release 4B and 14B models, including both the pre-trained base model and the instruction fine-tuned ones. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our models demonstrate competitive performance among open-source LMMs with similar model sizes. Our resulting LMMs demonstrate competitive performance among open-source LMMs with similar model sizes, with the ability to comprehend interleaved image-text inputs. Our training code, models, and all datasets used in this work, including the three largescale datasets we create and the preprocessed ones, will be open-sourced to better support the research community.

Yihan Cao, Siyu Li, Yixin Liu et al.

Recently, ChatGPT, along with DALL-E-2 and Codex,has been gaining significant attention from society. As a result, many individuals have become interested in related resources and are seeking to uncover the background and secrets behind its impressive performance. In fact, ChatGPT and other Generative AI (GAI) techniques belong to the category of Artificial Intelligence Generated Content (AIGC), which involves the creation of digital content, such as images, music, and natural language, through AI models. The goal of AIGC is to make the content creation process more efficient and accessible, allowing for the production of high-quality content at a faster pace. AIGC is achieved by extracting and understanding intent information from instructions provided by human, and generating the content according to its knowledge and the intent information. In recent years, large-scale models have become increasingly important in AIGC as they provide better intent extraction and thus, improved generation results. With the growth of data and the size of the models, the distribution that the model can learn becomes more comprehensive and closer to reality, leading to more realistic and high-quality content generation. This survey provides a comprehensive review on the history of generative models, and basic components, recent advances in AIGC from unimodal interaction and multimodal interaction. From the perspective of unimodality, we introduce the generation tasks and relative models of text and image. From the perspective of multimodality, we introduce the cross-application between the modalities mentioned above. Finally, we discuss the existing open problems and future challenges in AIGC.

Yixin Liu, Chenrui Fan, Yutong Dai et al.

Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this problem, existing poisoning-based approaches perturb user images in an imperceptible way to render them "unlearnable" from malicious uses. We identify two limitations of these defending approaches: i) sub-optimal due to the hand-crafted heuristics for solving the intractable bilevel optimization and ii) lack of robustness against simple data transformations like Gaussian filtering. To solve these challenges, we propose MetaCloak, which solves the bi-level poisoning problem with a meta-learning framework with an additional transformation sampling process to craft transferable and robust perturbation. Specifically, we employ a pool of surrogate diffusion models to craft transferable and model-agnostic perturbation. Furthermore, by incorporating an additional transformation process, we design a simple denoising-error maximization loss that is sufficient for causing transformation-robust semantic distortion and degradation in a personalized generation. Extensive experiments on the VGGFace2 and CelebA-HQ datasets show that MetaCloak outperforms existing approaches. Notably, MetaCloak can successfully fool online training services like Replicate, in a black-box manner, demonstrating the effectiveness of MetaCloak in real-world scenarios. Our code is available at https://github.com/liuyixin-louis/MetaCloak.

Zixuan Ye, Yutong Dai, Chaoyi Hong et al.

We study the composition style in deep image matting, a notion that characterizes a data generation flow on how to exploit limited foregrounds and random backgrounds to form a training dataset. Prior art executes this flow in a completely random manner by simply going through the foreground pool or by optionally combining two foregrounds before foreground-background composition. In this work, we first show that naive foreground combination can be problematic and therefore derive an alternative formulation to reasonably combine foregrounds. Our second contribution is an observation that matting performance can benefit from a certain occurrence frequency of combined foregrounds and their associated source foregrounds during training. Inspired by this, we introduce a novel composition style that binds the source and combined foregrounds in a definite triplet. In addition, we also find that different orders of foreground combination lead to different foreground patterns, which further inspires a quadruplet-based composition style. Results under controlled experiments on four matting baselines show that our composition styles outperform existing ones and invite consistent performance improvement on both composited and real-world datasets. Code is available at: https://github.com/coconuthust/composition_styles

Yutong Dai, Zeyuan Chen, Junnan Li et al.

Data heterogeneity across clients in federated learning (FL) settings is a widely acknowledged challenge. In response, personalized federated learning (PFL) emerged as a framework to curate local models for clients' tasks. In PFL, a common strategy is to develop local and global models jointly - the global model (for generalization) informs the local models, and the local models (for personalization) are aggregated to update the global model. A key observation is that if we can improve the generalization ability of local models, then we can improve the generalization of global models, which in turn builds better personalized models. In this work, we consider class imbalance, an overlooked type of data heterogeneity, in the classification setting. We propose FedNH, a novel method that improves the local models' performance for both personalization and generalization by combining the uniformity and semantics of class prototypes. FedNH initially distributes class prototypes uniformly in the latent space and smoothly infuses the class semantics into class prototypes. We show that imposing uniformity helps to combat prototype collapse while infusing class semantics improves local models. Extensive experiments were conducted on popular classification datasets under the cross-device setting. Our results demonstrate the effectiveness and stability of our method over recent works.

Kai Zhang, Yutong Dai, Hongyi Wang et al.

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT devices with varying memory capabilities, would limit the scale and hence the performance of the model could be trained. The mainstream approaches to address memory limitations focus on width-slimming techniques, where different clients train subnetworks with reduced widths locally and then the server aggregates the subnetworks. The global model produced from these methods suffers from performance degradation due to the negative impact of the actions taken to handle the varying subnetwork widths in the aggregation phase. In this paper, we introduce a memory-adaptive depth-wise learning solution in FL called FeDepth, which adaptively decomposes the full model into blocks according to the memory budgets of each client and trains blocks sequentially to obtain a full inference model. Our method outperforms state-of-the-art approaches, achieving 5% and more than 10% improvements in top-1 accuracy on CIFAR-10 and CIFAR-100, respectively. We also demonstrate the effectiveness of depth-wise fine-tuning on ViT. Our findings highlight the importance of memory-aware techniques for federated learning with heterogeneous devices and the success of depth-wise training strategy in improving the global model's performance.

Jun Yu, Yutong Dai, Xiaokang Liu et al.

MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a suite of benefits that enhance both the training process and the inference efficiency. MTL's key advantages encompass streamlined model architecture, performance enhancement, and cross-domain generalizability. Over the past twenty years, MTL has become widely recognized as a flexible and effective approach in various fields, including CV, NLP, recommendation systems, disease prognosis and diagnosis, and robotics. This survey provides a comprehensive overview of the evolution of MTL, encompassing the technical aspects of cutting-edge methods from traditional approaches to deep learning and the latest trend of pretrained foundation models. Our survey methodically categorizes MTL techniques into five key areas: regularization, relationship learning, feature propagation, optimization, and pre-training. This categorization not only chronologically outlines the development of MTL but also dives into various specialized strategies within each category. Furthermore, the survey reveals how the MTL evolves from handling a fixed set of tasks to embracing a more flexible approach free from task or modality constraints. It explores the concepts of task-promptable and -agnostic training, along with the capacity for ZSL, which unleashes the untapped potential of this historically coveted learning paradigm. Overall, we hope this survey provides the research community with a comprehensive overview of the advancements in MTL from its inception in 1997 to the present in 2023. We address present challenges and look ahead to future possibilities, shedding light on the opportunities and potential avenues for MTL research in a broad manner. This project is publicly available at https://github.com/junfish/Awesome-Multitask-Learning.

Taihui Li, Anish Lahiri, Yutong Dai et al.

Demosaicing and denoising of RAW images are crucial steps in the processing pipeline of modern digital cameras. As only a third of the color information required to produce a digital image is captured by the camera sensor, the process of demosaicing is inherently ill-posed. The presence of noise further exacerbates this problem. Performing these two steps sequentially may distort the content of the captured RAW images and accumulate errors from one step to another. Recent deep neural-network-based approaches have shown the effectiveness of joint demosaicing and denoising to mitigate such challenges. However, these methods typically require a large number of training samples and do not generalize well to different types and intensities of noise. In this paper, we propose a novel joint demosaicing and denoising method, dubbed JDD-DoubleDIP, which operates directly on a single RAW image without requiring any training data. We validate the effectiveness of our method on two popular datasets -- Kodak and McMaster -- with various noises and noise intensities. The experimental results show that our method consistently outperforms other compared methods in terms of PSNR, SSIM, and qualitative visual perception.

Luyu Yang, Yutong Dai, An Yan et al.

The physical world is not merely visual; it is governed by rigorous structural and procedural constraints. Yet, the evaluation of vision-language models (VLMs) remains heavily skewed toward perceptual realism, prioritizing the generation of visually plausible 3D layouts, shapes, and appearances. Current benchmarks rarely test whether models grasp the step-by-step processes and physical dependencies required to actually build these artifacts, a capability essential for automating design-to-construction pipelines. To address this, we introduce DreamHouse, a novel benchmark for physical generative reasoning: the capacity to synthesize artifacts that concurrently satisfy geometric, structural, constructability, and code-compliance constraints. We ground this benchmark in residential timber-frame construction, a domain with fully codified engineering standards and objectively verifiable correctness. We curate over 26,000 structures spanning 13 architectural styles, ach verified to construction-document standards (LOD 350) and develop a deterministic 10-test structural validation framework. Unlike static benchmarks that assess only final outputs, DreamHouse supports iterative agentic interaction. Models observe intermediate build states, generate construction actions, and receive structured environmental feedback, enabling a fine-grained evaluation of planning, structural reasoning, and self-correction. Extensive experiments with state-of-the-art VLMs reveal substantial capability gaps that are largely invisible on existing leaderboards. These findings establish physical validity as a critical evaluation axis orthogonal to visual realism, highlighting physical generative reasoning as a distinct and underdeveloped frontier in multimodal intelligence. Available at https://luluyuyuyang.github.io/dreamhouse

Yutong Dai, Krithika Ramakrishnan, Jing Gu et al.

We introduce SCUBA, a benchmark designed to evaluate computer-use agents on customer relationship management (CRM) workflows within the Salesforce platform. SCUBA contains 300 task instances derived from real user interviews, spanning three primary personas, platform administrators, sales representatives, and service agents. The tasks test a range of enterprise-critical abilities, including Enterprise Software UI navigation, data manipulation, workflow automation, information retrieval, and troubleshooting. To ensure realism, SCUBA operates in Salesforce sandbox environments with support for parallel execution and fine-grained evaluation metrics to capture milestone progress. We benchmark a diverse set of agents under both zero-shot and demonstration-augmented settings. We observed huge performance gaps in different agent design paradigms and gaps between the open-source model and the closed-source model. In the zero-shot setting, open-source model powered computer-use agents that have strong performance on related benchmarks like OSWorld only have less than 5\% success rate on SCUBA, while methods built on closed-source models can still have up to 39% task success rate. In the demonstration-augmented settings, task success rates can be improved to 50\% while simultaneously reducing time and costs by 13% and 16%, respectively. These findings highlight both the challenges of enterprise tasks automation and the promise of agentic solutions. By offering a realistic benchmark with interpretable evaluation, SCUBA aims to accelerate progress in building reliable computer-use agents for complex business software ecosystems.

Yan Yang, Dongxu Li, Yutong Dai et al.

Graphical user interface (GUI) agents autonomously complete tasks across platforms (\eg, Linux) by sequentially decomposing user instructions into action proposals that iteratively interact with visual elements in the evolving environment. However, two main challenges arise: i) planning (\ie, the action proposal sequence) under expansive action space, where selecting an appropriate plan is non-trivial, as many valid ones may exist; ii) accurately grounding actions in complex and high-resolution interfaces, \ie, precisely interacting with visual targets. This paper investigates the aforementioned challenges with our \textbf{G}UI \textbf{T}est-time Scaling \textbf{A}gent, namely GTA1. First, we conduct test-time scaling to select the most appropriate action proposal: at each step, multiple candidate proposals are sampled and evaluated and selected by a judge model. It trades off computation for better decision quality by concurrent sampling. Second, we propose a model that improves grounding of the selected action proposals to its corresponding visual elements. Our key insight is that reinforcement learning (RL) facilitates grounding through inherent objective alignments, rewarding successful clicks on interface elements. Experimentally, GTA1 achieves state-of-the-art performance on both grounding and agent task execution benchmarks. The code and models are released here.

Linxin Song, Yutong Dai, Viraj Prabhu et al.

Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they remain constrained by the inherent limitations of performing all actions through GUI manipulation, leading to brittleness and inefficiency. In this work, we introduce a more robust and flexible paradigm: enabling agents to use coding as a enhanced action. We present CoAct-1, a novel multi-agent system that synergistically combines GUI-based control with direct programmatic execution. CoAct-1 features an Orchestrator that dynamically delegates subtasks to either a conventional GUI Operator or a specialized Programmer agent, which can write and execute Python or Bash scripts. This hybrid approach allows the agent to bypass inefficient GUI action sequences for tasks like file management and data processing, while still leveraging visual interaction when necessary. We evaluate our system on the challenging OSWorld benchmark, where CoAct-1 achieves a new state-of-the-art success rate of 60.76%, significantly outperforming prior methods. Furthermore, our approach dramatically improves efficiency, reducing the average number of steps required to complete a task to just 10.15, compared to 15 for leading GUI agents. Our results demonstrate that integrating coding as a core action provides a more powerful, efficient, and scalable path toward generalized computer automation.

Chaoyue Niu, Yucheng Ding, Junhui Lu et al.

The conventional cloud-based large model learning framework is increasingly constrained by latency, cost, personalization, and privacy concerns. In this survey, we explore an emerging paradigm: collaborative learning between on-device small model and cloud-based large model, which promises low-latency, cost-efficient, and personalized intelligent services while preserving user privacy. We provide a comprehensive review across hardware, system, algorithm, and application layers. At each layer, we summarize key problems and recent advances from both academia and industry. In particular, we categorize collaboration algorithms into data-based, feature-based, and parameter-based frameworks. We also review publicly available datasets and evaluation metrics with user-level or device-level consideration tailored to collaborative learning settings. We further highlight real-world deployments, ranging from recommender systems and mobile livestreaming to personal intelligent assistants. We finally point out open research directions to guide future development in this rapidly evolving field.

Dezhong Yao, Sanmu Li, Yutong Dai et al.

Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time. The constraints of storage limitations and privacy concerns confine local models to exclusively access the present data within each learning cycle. Consequently, this restriction induces performance degradation in model training on previous data, termed "catastrophic forgetting". However, existing FCL approaches need to identify or know changes in data distribution, which is difficult in the real world. To release these limitations, this paper directs attention to a broader continuous framework. Within this framework, we introduce Federated Bayesian Neural Network (FedBNN), a versatile and efficacious framework employing a variational Bayesian neural network across all clients. Our method continually integrates knowledge from local and historical data distributions into a single model, adeptly learning from new data distributions while retaining performance on historical distributions. We rigorously evaluate FedBNN's performance against prevalent methods in federated learning and continual learning using various metrics. Experimental analyses across diverse datasets demonstrate that FedBNN achieves state-of-the-art results in mitigating forgetting.

Kung-Hsiang Huang, Haoyi Qiu, Yutong Dai et al.

Graphical user interface (GUI) agents built on vision-language models have emerged as a promising approach to automate human-computer workflows. However, they also face the inefficiency challenge as they process long sequences of high-resolution screenshots and solving long-horizon tasks, making inference slow, costly and memory-bound. While key-value (KV) caching can mitigate this, storing the full cache is prohibitive for image-heavy contexts. Existing cache-compression methods are sub-optimal as they do not account for the spatial and temporal redundancy of GUIs. In this work, we first analyze attention patterns in GUI agent workloads and find that, unlike in natural images, attention sparsity is uniformly high across all transformer layers. This insight motivates a simple uniform budget allocation strategy, which we show empirically outperforms more complex layer-varying schemes. Building on this, we introduce GUI-KV, a plug-and-play KV cache compression method for GUI agents that requires no retraining. GUI-KV combines two novel techniques: (i) spatial saliency guidance, which augments attention scores with the L2 norm of hidden states to better preserve semantically important visual tokens, and (ii) temporal redundancy scoring, which projects previous frames' keys onto the current frame's key subspace to preferentially prune redundant history. Across standard GUI agent benchmarks and models, GUI-KV outperforms competitive KV compression baselines, closely matching full-cache accuracy at modest budgets. Notably, in a 5-screenshot setting on the AgentNetBench benchmark, GUI-KV reduces decoding FLOPs by 38.9% while increasing step accuracy by 4.1% over the full-cache baseline. These results demonstrate that exploiting GUI-specific redundancies enables efficient and reliable agent performance.

Andrew Y Guo, Anagh Malik, SaiKiran Tedla et al.

We introduce Dark3R, a framework for structure from motion in the dark that operates directly on raw images with signal-to-noise ratios (SNRs) below $-4$ dB -- a regime where conventional feature- and learning-based methods break down. Our key insight is to adapt large-scale 3D foundation models to extreme low-light conditions through a teacher--student distillation process, enabling robust feature matching and camera pose estimation in low light. Dark3R requires no 3D supervision; it is trained solely on noisy--clean raw image pairs, which can be either captured directly or synthesized using a simple Poisson--Gaussian noise model applied to well-exposed raw images. To train and evaluate our approach, we introduce a new, exposure-bracketed dataset that includes $\sim$42,000 multi-view raw images with ground-truth 3D annotations, and we demonstrate that Dark3R achieves state-of-the-art structure from motion in the low-SNR regime. Further, we demonstrate state-of-the-art novel view synthesis in the dark using Dark3R's predicted poses and a coarse-to-fine radiance field optimization procedure.

Wanzhe Xu, Yutong Dai, Yitao Yang et al.

Accurate multivariate time-series prediction of vital signs and laboratory results is crucial for early intervention and precision medicine in intensive care units (ICUs). However, vital signs are often noisy and exhibit rapid fluctuations, while laboratory tests suffer from missing values, measurement lags, and device-specific bias, making integrative forecasting highly challenging. To address these issues, we propose OmniTFT, a deep learning framework that jointly learns and forecasts high-frequency vital signs and sparsely sampled laboratory results based on the Temporal Fusion Transformer (TFT). Specifically, OmniTFT implements four novel strategies to enhance performance: sliding window equalized sampling to balance physiological states, frequency-aware embedding shrinkage to stabilize rare-class representations, hierarchical variable selection to guide model attention toward informative feature clusters, and influence-aligned attention calibration to enhance robustness during abrupt physiological changes. By reducing the reliance on target-specific architectures and extensive feature engineering, OmniTFT enables unified modeling of multiple heterogeneous clinical targets while preserving cross-institutional generalizability. Across forecasting tasks, OmniTFT achieves substantial performance improvement for both vital signs and laboratory results on the MIMIC-III, MIMIC-IV, and eICU datasets. Its attention patterns are interpretable and consistent with known pathophysiology, underscoring its potential utility for quantitative decision support in clinical care.

Viraj Prabhu, Yutong Dai, Matthew Fernandez et al.

Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by contrast, exploit website-provided functionality through high-level operations like search, filter, and sort. We introduce WALT (Web Agents that Learn Tools), a framework that reverse-engineers latent website functionality into reusable invocable tools. Rather than hypothesizing ad-hoc skills, WALT exposes robust implementations of automations already designed into websites -- spanning discovery (search, filter, sort), communication (post, comment, upvote), and content management (create, edit, delete). Tools abstract away low-level execution: instead of reasoning about how to click and type, agents simply call search(query) or create(listing). This shifts the computational burden from fragile step-by-step reasoning to reliable tool invocation. On VisualWebArena and WebArena, WALT achieves higher success with fewer steps and less LLM-dependent reasoning, establishing a robust and generalizable paradigm for browser automation.

Yutong Dai, Brian Price, He Zhang et al.

Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is still under-explored. Although some works propose to either refine the trimaps or adapt the algorithms to real-world images via extra data augmentation, none of them has taken both into consideration, not to mention the significant performance deterioration on benchmarks while using those data augmentation. To fill this gap, we propose an image matting method which achieves higher robustness (RMat) via multilevel context assembling and strong data augmentation targeting matting. Specifically, we first build a strong matting framework by modeling ample global information with transformer blocks in the encoder, and focusing on details in combination with convolution layers as well as a low-level feature assembling attention block in the decoder. Then, based on this strong baseline, we analyze current data augmentation and explore simple but effective strong data augmentation to boost the baseline model and contribute a more generalizable matting method. Compared with previous methods, the proposed method not only achieves state-of-the-art results on the Composition-1k benchmark (11% improvement on SAD and 27% improvement on Grad) with smaller model size, but also shows more robust generalization results on other benchmarks, on real-world images, and also on varying coarse-to-fine trimaps with our extensive experiments.

Dezhong Yao, Wanning Pan, Michael J O'Neill et al.

One underlying assumption of recent federated learning (FL) paradigms is that all local models usually share the same network architecture and size, which becomes impractical for devices with different hardware resources. A scalable federated learning framework should address the heterogeneity that clients have different computing capacities and communication capabilities. To this end, this paper proposes FedHM, a novel heterogeneous federated model compression framework, distributing the heterogeneous low-rank models to clients and then aggregating them into a full-rank model. Our solution enables the training of heterogeneous models with varying computational complexities and aggregates them into a single global model. Furthermore, FedHM significantly reduces the communication cost by using low-rank models. Extensive experimental results demonstrate that FedHM is superior in the performance and robustness of models of different sizes, compared with state-of-the-art heterogeneous FL methods under various FL settings. Additionally, the convergence guarantee of FL for heterogeneous devices is first theoretically analyzed.

Dezhong Yao, Wanning Pan, Yutong Dai et al.

Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, due to the heterogeneity of the system and data, many approaches suffer from the "client-drift" issue that could significantly slow down the convergence of the global model training. As clients perform local updates on heterogeneous data through heterogeneous systems, their local models drift apart. To tackle this issue, one intuitive idea is to guide the local model training by the global teachers, i.e., past global models, where each client learns the global knowledge from past global models via adaptive knowledge distillation techniques. Coming from these insights, we propose a novel approach for heterogeneous federated learning, namely FedGKD, which fuses the knowledge from historical global models for local training to alleviate the "client-drift" issue. In this paper, we evaluate FedGKD with extensive experiments on various CV/NLP datasets (i.e., CIFAR-10/100, Tiny-ImageNet, AG News, SST5) and different heterogeneous settings. The proposed method is guaranteed to converge under common assumptions, and achieves superior empirical accuracy in fewer communication runs than five state-of-the-art methods.

Yutong Dai, Hao Lu, Chunhua Shen

We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. Second-order features are commonly used in dense prediction to build adjacent relations with a learnable module after upsampling such as non-local blocks. Since upsampling is essential, learning affinity in upsampling can avoid additional propagation layers, offering the potential for building compact models. By looking at existing upsampling operators from a unified mathematical perspective, we generalize them into a second-order form and introduce Affinity-Aware Upsampling (A2U) where upsampling kernels are generated using a light-weight lowrank bilinear model and are conditioned on second-order features. Our upsampling operator can also be extended to downsampling. We discuss alternative implementations of A2U and verify their effectiveness on two detail-sensitive tasks: image reconstruction on a toy dataset; and a largescale image matting task where affinity-based ideas constitute mainstream matting approaches. In particular, results on the Composition-1k matting dataset show that A2U achieves a 14% relative improvement in the SAD metric against a strong baseline with negligible increase of parameters (<0.5%). Compared with the state-of-the-art matting network, we achieve 8% higher performance with only 40% model complexity.

Yu Liu, Yutong Dai, Anh-Dzung Doan et al.

As a milestone for video object segmentation, one-shot video object segmentation (OSVOS) has achieved a large margin compared to the conventional optical-flow based methods regarding to the segmentation accuracy. Its excellent performance mainly benefit from the three-step training mechanism, that are: (1) acquiring object features on the base dataset (i.e. ImageNet), (2) training the parent network on the training set of the target dataset (i.e. DAVIS-2016) to be capable of differentiating the object of interest from the background. (3) online fine-tuning the interested object on the first frame of the target test set to overfit its appearance, then the model can be utilized to segment the same object in the rest frames of that video. In this paper, we argue that for the step (2), OSVOS has the limitation to 'overemphasize' the generic semantic object information while 'dilute' the instance cues of the object(s), which largely block the whole training process. Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i.e. online fine-tuning on the target instance. Through extensive experiments using different network structures as the backbone, we show that the proposed video loss module can improve the segmentation performance significantly, compared to that of OSVOS. Meanwhile, since video loss is a common module, it can be generalized to other fine-tuning based methods and similar vision tasks such as depth estimation and saliency detection.

Hao Lu, Yutong Dai, Chunhua Shen et al.

We show that existing upsampling operators can be unified using the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can often recover boundary details considerably better than other upsampling operators such as bilinear interpolation. By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision. At the core of this framework is a new learnable module, termed Index Network (IndexNet), which dynamically generates indices conditioned on the feature map itself. IndexNet can be used as a plug-in applying to almost all off-the-shelf convolutional networks that have coupled downsampling and upsampling stages, giving the networks the ability to dynamically capture variations of local patterns. In particular, we instantiate and investigate five families of IndexNet and demonstrate their effectiveness on four dense prediction tasks, including image denoising, image matting, semantic segmentation, and monocular depth estimation. Code and models have been made available at: https://tinyurl.com/IndexNetV1

Hao Lu, Yutong Dai, Chunhua Shen et al.

We show that existing upsampling operators can be unified with the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can recover boundary details much better than other upsampling operators such as bilinear interpolation. By looking at the indices as a function of the feature map, we introduce the concept of learning to index, and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the pooling and upsampling operators, without the need of supervision. At the core of this framework is a flexible network module, termed IndexNet, which dynamically predicts indices given an input. Due to its flexibility, IndexNet can be used as a plug-in applying to any off-the-shelf convolutional networks that have coupled downsampling and upsampling stages. We demonstrate the effectiveness of IndexNet on the task of natural image matting where the quality of learned indices can be visually observed from predicted alpha mattes. Results on the Composition-1k matting dataset show that our model built on MobileNetv2 exhibits at least $16.1\%$ improvement over the seminal VGG-16 based deep matting baseline, with less training data and lower model capacity. Code and models has been made available at: https://tinyurl.com/IndexNetV1