Improved Visual Fine-tuning with Natural Language Supervision

Fine-tuning a pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream tasks with limited training examples. While the problem of catastrophic forgetting in backbone has been extensively studied, the potential bias existing in a pre-trained model due to the corresponding pre-training task and data, attracts less attention. In this work, we investigate this problem by demonstrating that the obtained classifier after fine-tuning will be close to that induced by the pre-trained model. To reduce the bias in the classifier effectively, we introduce a reference distribution obtained from a fixed text classifier, which can help regularize the learned vision classifier. The proposed method, Text Supervised fine-tuning (TeS), is evaluated with diverse pre-trained vision models including ResNet and ViT, and text encoders including BERT and CLIP, on 11 downstream tasks. The consistent improvement with a clear margin over distinct scenarios confirms the effectiveness of our proposal.

CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions

Motion capture is a long-standing research problem. Although it has been studied for decades, the majority of research focus on ground-based movements such as walking, sitting, dancing, etc. Off-grounded actions such as climbing are largely overlooked. As an important type of action in sports and firefighting field, the climbing movements is challenging to capture because of its complex back poses, intricate human-scene interactions, and difficult global localization. The research community does not have an in-depth understanding of the climbing action due to the lack of specific datasets. To address this limitation, we collect CIMI4D, a large rock \textbf{C}l\textbf{I}mbing \textbf{M}ot\textbf{I}on dataset from 12 persons climbing 13 different climbing walls. The dataset consists of around 180,000 frames of pose inertial measurements, LiDAR point clouds, RGB videos, high-precision static point cloud scenes, and reconstructed scene meshes. Moreover, we frame-wise annotate touch rock holds to facilitate a detailed exploration of human-scene interaction. The core of this dataset is a blending optimization process, which corrects for the pose as it drifts and is affected by the magnetic conditions. To evaluate the merit of CIMI4D, we perform four tasks which include human pose estimations (with/without scene constraints), pose prediction, and pose generation. The experimental results demonstrate that CIMI4D presents great challenges to existing methods and enables extensive research opportunities. We share the dataset with the research community in http://www.lidarhumanmotion.net/cimi4d/.

Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval

Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the following practical assumptions: (i) no correspondence relationship, and (ii) no category annotations. It is challenging to align and bridge distinct domains without cross-domain correspondence. To tackle the challenge, we present a novel Correspondence-free Domain Alignment (CoDA) method to effectively eliminate the cross-domain gap through In-domain Self-matching Supervision (ISS) and Cross-domain Classifier Alignment (CCA). To be specific, ISS is presented to encapsulate discriminative information into the latent common space by elaborating a novel self-matching supervision mechanism. To alleviate the cross-domain discrepancy, CCA is proposed to align distinct domain-specific classifiers. Thanks to the ISS and CCA, our method could encode the discrimination into the domain-invariant embedding space for unsupervised cross-domain image retrieval. To verify the effectiveness of the proposed method, extensive experiments are conducted on four benchmark datasets compared with six state-of-the-art methods.

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video

Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality collaboration while addressing the problem of modality entanglement. In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement. It is flexible to select different modules for different understanding and generation tasks across all modalities including text, image, and video. Empirical study shows that mPLUG-2 achieves state-of-the-art or competitive results on a broad range of over 30 downstream tasks, spanning multi-modal tasks of image-text and video-text understanding and generation, and uni-modal tasks of text-only, image-only, and video-only understanding. Notably, mPLUG-2 shows new state-of-the-art results of 48.0 top-1 accuracy and 80.3 CIDEr on the challenging MSRVTT video QA and video caption tasks with a far smaller model size and data scale. It also demonstrates strong zero-shot transferability on vision-language and video-language tasks. Code and models will be released in https://github.com/alibaba/AliceMind.

Learning Trajectory-Word Alignments for Video-Language Tasks

Aligning objects with words plays a critical role in Image-Language BERT (IL-BERT) and Video-Language BERT (VDL-BERT). Different from the image case where an object covers some spatial patches, an object in a video usually appears as an object trajectory, i.e., it spans over a few spatial but longer temporal patches and thus contains abundant spatiotemporal contexts. However, modern VDL-BERTs neglect this trajectory characteristic that they usually follow IL-BERTs to deploy the patch-to-word (P2W) attention while such attention may over-exploit trivial spatial contexts and neglect significant temporal contexts. To amend this, we propose a novel TW-BERT to learn Trajectory-Word alignment for solving video-language tasks. Such alignment is learned by a newly designed trajectory-to-word (T2W) attention. Besides T2W attention, we also follow previous VDL-BERTs to set a word-to-patch (W2P) attention in the cross-modal encoder. Since T2W and W2P attentions have diverse structures, our cross-modal encoder is asymmetric. To further help this asymmetric cross-modal encoder build robust vision-language associations, we propose a fine-grained ``align-before-fuse'' strategy to pull close the embedding spaces calculated by the video and text encoders. By the proposed strategy and T2W attention, our TW-BERT achieves SOTA performances on text-to-video retrieval tasks, and comparable performances on video question answering tasks with some VDL-BERTs trained on much more data. The code will be available in the supplementary material.

HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training

Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus not fully exploiting the unique characteristic of video, i.e., temporal. In this paper, we propose a Hierarchical Temporal-Aware video-language pre-training framework, HiTeA, with two novel pre-training tasks for modeling cross-modal alignment between moments and texts as well as the temporal relations of video-text pairs. Specifically, we propose a cross-modal moment exploration task to explore moments in videos, which results in detailed video moment representation. Besides, the inherent temporal relations are captured by aligning video-text pairs as a whole in different time resolutions with multi-modal temporal relation exploration task. Furthermore, we introduce the shuffling test to evaluate the temporal reliance of datasets and video-language pre-training models. We achieve state-of-the-art results on 15 well-established video-language understanding and generation tasks, especially on temporal-oriented datasets (e.g., SSv2-Template and SSv2-Label) with 8.6% and 11.1% improvement respectively. HiTeA also demonstrates strong generalization ability when directly transferred to downstream tasks in a zero-shot manner. Models and demo will be available on ModelScope.

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical. However, such constraint not only excludes low-end clients who would otherwise make unique contributions to model training but also restrains clients from training large models due to on-device resource bottlenecks. In this work, we propose FedRolex, a partial training (PT)-based approach that enables model-heterogeneous FL and can train a global server model larger than the largest client model. At its core, FedRolex employs a rolling sub-model extraction scheme that allows different parts of the global server model to be evenly trained, which mitigates the client drift induced by the inconsistency between individual client models and server model architectures. We show that FedRolex outperforms state-of-the-art PT-based model-heterogeneous FL methods (e.g. Federated Dropout) and reduces the gap between model-heterogeneous and model-homogeneous FL, especially under the large-model large-dataset regime. In addition, we provide theoretical statistical analysis on its advantage over Federated Dropout and evaluate FedRolex on an emulated real-world device distribution to show that FedRolex can enhance the inclusiveness of FL and boost the performance of low-end devices that would otherwise not benefit from FL. Our code is available at https://github.com/MSU-MLSys-Lab/FedRolex.

Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks like zero-shot image captioning remains unsatisfied. In this work, we discuss that directly employing CLIP for zero-shot image captioning relies more on the textual modality in context and largely ignores the visual information, which we call \emph{contextual language prior}. To address this, we propose Cross-modal Language Models (CLMs) to facilitate unsupervised cross-modal learning. We further propose Anchor Augment to guide the generative model's attention to the fine-grained information in the representation of CLIP. Experiments on MS COCO and Flickr 30K validate the promising performance of proposed approach in both captioning quality and computational efficiency.

Eye-tracking based classification of Mandarin Chinese readers with and without dyslexia using neural sequence models

Eye movements are known to reflect cognitive processes in reading, and psychological reading research has shown that eye gaze patterns differ between readers with and without dyslexia. In recent years, researchers have attempted to classify readers with dyslexia based on their eye movements using Support Vector Machines (SVMs). However, these approaches (i) are based on highly aggregated features averaged over all words read by a participant, thus disregarding the sequential nature of the eye movements, and (ii) do not consider the linguistic stimulus and its interaction with the reader's eye movements. In the present work, we propose two simple sequence models that process eye movements on the entire stimulus without the need of aggregating features across the sentence. Additionally, we incorporate the linguistic stimulus into the model in two ways -- contextualized word embeddings and manually extracted linguistic features. The models are evaluated on a Mandarin Chinese dataset containing eye movements from children with and without dyslexia. Our results show that (i) even for a logographic script such as Chinese, sequence models are able to classify dyslexia on eye gaze sequences, reaching state-of-the-art performance, and (ii) incorporating the linguistic stimulus does not help to improve classification performance.

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

Decentralized optimization is an emerging paradigm in distributed learning in which agents achieve network-wide solutions by peer-to-peer communication without the central server. Since communication tends to be slower than computation, when each agent communicates with only a few neighboring agents per iteration, they can complete iterations faster than with more agents or a central server. However, the total number of iterations to reach a network-wide solution is affected by the speed at which the agents' information is ``mixed'' by communication. We found that popular communication topologies either have large maximum degrees (such as stars and complete graphs) or are ineffective at mixing information (such as rings and grids). To address this problem, we propose a new family of topologies, EquiTopo, which has an (almost) constant degree and a network-size-independent consensus rate that is used to measure the mixing efficiency. In the proposed family, EquiStatic has a degree of $\Theta(\ln(n))$, where $n$ is the network size, and a series of time-dependent one-peer topologies, EquiDyn, has a constant degree of 1. We generate EquiDyn through a certain random sampling procedure. Both of them achieve an $n$-independent consensus rate. We apply them to decentralized SGD and decentralized gradient tracking and obtain faster communication and better convergence, theoretically and empirically. Our code is implemented through BlueFog and available at \url{https://github.com/kexinjinnn/EquiTopo}