SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training

In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trained models (PTMs) can greatly facilitate knowledge transfer and alleviate catastrophic forgetting, but also suffers from progressive overfitting of pre-trained knowledge into specific downstream tasks. A majority of current efforts often keep the PTMs frozen and incorporate task-specific prompts to instruct representation learning, coupled with a prompt selection process for inference. However, due to the limited capacity of prompt parameters, this strategy demonstrates only sub-optimal performance in continual learning. In comparison, tuning all parameters of PTMs often provides the greatest potential for representation learning, making sequential fine-tuning (Seq FT) a fundamental baseline that has been overlooked in CLPT. To this end, we present an in-depth analysis of the progressive overfitting problem from the lens of Seq FT. Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Classifier Alignment (SLCA++) framework to unleash the power of Seq FT, serving as a strong baseline approach for CLPT. Our approach involves a Slow Learner to selectively reduce the learning rate of backbone parameters, and a Classifier Alignment to align the disjoint classification layers in a post-hoc fashion. We further enhance the efficacy of SL with a symmetric cross-entropy loss, as well as employ a parameter-efficient strategy to implement Seq FT with SLCA++. Across a variety of continual learning scenarios on image classification benchmarks, our approach provides substantial improvements and outperforms state-of-the-art methods by a large margin. Code: https://github.com/GengDavid/SLCA.

ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation

Recent works utilize CLIP to perform the challenging unsupervised semantic segmentation task where only images without annotations are available. However, we observe that when adopting CLIP to such a pixel-level understanding task, unexpected bias (including class-preference bias and space-preference bias) occurs. Previous works don't explicitly model the bias, which largely constrains the segmentation performance. In this paper, we propose to explicitly model and rectify the bias existing in CLIP to facilitate the unsupervised semantic segmentation task. Specifically, we design a learnable ''Reference'' prompt to encode class-preference bias and a projection of the positional embedding in vision transformer to encode space-preference bias respectively. To avoid interference, two kinds of biases are firstly independently encoded into the Reference feature and the positional feature. Via a matrix multiplication between two features, a bias logit map is generated to explicitly represent two kinds of biases. Then we rectify the logits of CLIP via a simple element-wise subtraction. To make the rectified results smoother and more contextual, we design a mask decoder which takes the feature of CLIP and rectified logits as input and outputs a rectified segmentation mask with the help of Gumbel-Softmax operation. To make the bias modeling and rectification process meaningful and effective, a contrastive loss based on masked visual features and the text features of different classes is imposed. To further improve the segmentation, we distill the knowledge from the rectified CLIP to the advanced segmentation architecture via minimizing our designed mask-guided, feature-guided and text-guided loss terms. Extensive experiments on various benchmarks demonstrate that ReCLIP++ performs favorably against previous SOTAs. The implementation is available at: https://github.com/dogehhh/ReCLIP.

VISA: Reasoning Video Object Segmentation via Large Language Models

Existing Video Object Segmentation (VOS) relies on explicit user instructions, such as categories, masks, or short phrases, restricting their ability to perform complex video segmentation requiring reasoning with world knowledge. In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS). This task aims to generate a sequence of segmentation masks in response to implicit text queries that require complex reasoning abilities based on world knowledge and video contexts, which is crucial for structured environment understanding and object-centric interactions, pivotal in the development of embodied AI. To tackle ReasonVOS, we introduce VISA (Video-based large language Instructed Segmentation Assistant), to leverage the world knowledge reasoning capabilities of multi-modal LLMs while possessing the ability to segment and track objects in videos with a mask decoder. Moreover, we establish a comprehensive benchmark consisting of 35,074 instruction-mask sequence pairs from 1,042 diverse videos, which incorporates complex world knowledge reasoning into segmentation tasks for instruction-tuning and evaluation purposes of ReasonVOS models. Experiments conducted on 8 datasets demonstrate the effectiveness of VISA in tackling complex reasoning segmentation and vanilla referring segmentation in both video and image domains. The code and dataset are available at https://github.com/cilinyan/VISA.

Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning

Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge embedded in CLIP. Previous work mines the knowledge typically based on the limited visual samples and close-set semantics (i.e., within target category set of downstream task). However, the aligned CLIP image/text encoders contain abundant relationships between visual features and almost infinite open semantics, which may benefit the few-shot learning but remains unexplored. In this paper, we propose to mine open semantics as anchors to perform a relation transition from image-anchor relationship to image-target relationship to make predictions. Specifically, we adopt a transformer module which takes the visual feature as "Query", the text features of the anchors as "Key" and the similarity matrix between the text features of anchor and target classes as "Value". In this way, the output of such a transformer module represents the relationship between the image and target categories, i.e., the classification predictions. To avoid manually selecting the open semantics, we make the [CLASS] token of input text embedding learnable. We conduct extensive experiments on eleven representative classification datasets. The results show that our method performs favorably against previous state-of-the-arts considering few-shot classification settings.

Tuning-Free Inversion-Enhanced Control for Consistent Image Editing

Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e.g., changing postures) to the main objects in the input image without changing their identity or attributes. To guarantee consistent attributes, some existing methods fine-tune the entire model or the textual embedding for structural consistency, but they are time-consuming and fail to perform non-rigid edits. Other works are tuning-free, but their performances are weakened by the quality of Denoising Diffusion Implicit Model (DDIM) reconstruction, which often fails in real-world scenarios. In this paper, we present a novel approach called Tuning-free Inversion-enhanced Control (TIC), which directly correlates features from the inversion process with those from the sampling process to mitigate the inconsistency in DDIM reconstruction. Specifically, our method effectively obtains inversion features from the key and value features in the self-attention layers, and enhances the sampling process by these inversion features, thus achieving accurate reconstruction and content-consistent editing. To extend the applicability of our method to general editing scenarios, we also propose a mask-guided attention concatenation strategy that combines contents from both the inversion and the naive DDIM editing processes. Experiments show that the proposed method outperforms previous works in reconstruction and consistent editing, and produces impressive results in various settings.

LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation

Leveraging the generative ability of image diffusion models offers great potential for zero-shot video-to-video translation. The key lies in how to maintain temporal consistency across generated video frames by image diffusion models. Previous methods typically adopt cross-frame attention, \emph{i.e.,} sharing the \textit{key} and \textit{value} tokens across attentions of different frames, to encourage the temporal consistency. However, in those works, temporal inconsistency issue may not be thoroughly solved, rendering the fidelity of generated videos limited.%The current state of the art cross-frame attention method aims at maintaining fine-grained visual details across frames, but it is still challenged by the temporal coherence problem. In this paper, we find the bottleneck lies in the unconstrained query tokens and propose a new zero-shot video-to-video translation framework, named \textit{LatentWarp}. Our approach is simple: to constrain the query tokens to be temporally consistent, we further incorporate a warping operation in the latent space to constrain the query tokens. Specifically, based on the optical flow obtained from the original video, we warp the generated latent features of last frame to align with the current frame during the denoising process. As a result, the corresponding regions across the adjacent frames can share closely-related query tokens and attention outputs, which can further improve latent-level consistency to enhance visual temporal coherence of generated videos. Extensive experiment results demonstrate the superiority of \textit{LatentWarp} in achieving video-to-video translation with temporal coherence.

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. Previous works adopt the conventional classification architecture, which consists of a feature extractor and a classifier. The feature extractor is shared across sequentially arrived tasks or classes, but one specific group of weights of the classifier corresponding to one new class should be incrementally expanded. Consequently, the parameters of a continual learner gradually increase. Moreover, as the classifier contains all historical arrived classes, a certain size of the memory is usually required to store rehearsal data to mitigate classifier bias and catastrophic forgetting. In this paper, we propose a non-incremental learner, named AttriCLIP, to incrementally extract knowledge of new classes or tasks. Specifically, AttriCLIP is built upon the pre-trained visual-language model CLIP. Its image encoder and text encoder are fixed to extract features from both images and text. Text consists of a category name and a fixed number of learnable parameters which are selected from our designed attribute word bank and serve as attributes. As we compute the visual and textual similarity for classification, AttriCLIP is a non-incremental learner. The attribute prompts, which encode the common knowledge useful for classification, can effectively mitigate the catastrophic forgetting and avoid constructing a replay memory. We evaluate our AttriCLIP and compare it with CLIP-based and previous state-of-the-art continual learning methods in realistic settings with domain-shift and long-sequence learning. The results show that our method performs favorably against previous state-of-the-arts. The implementation code can be available at https://github.com/bhrqw/AttriCLIP.

PiClick: Picking the desired mask in click-based interactive segmentation

Click-based interactive segmentation enables productive pixel-level annotation and image editing with simple user clicks, whereas target ambiguity remains a problem hindering precise segmentation. That is, in scenes with rich context, one click may refer to multiple potential targets residing in corresponding masks, while most interactive segmentors can only generate one single mask and fail to capture the rich context. To resolve target ambiguity, we here propose PiClick to produce semantically diversified masks. PiClick leverages a transformer network design wherein mutually interactive mask queries are integrated to infuse target priors. Moreover, a Target Reasoning Module is designed in PiClick to automatically imply the best-matched mask from all proposals, significantly relieving target ambiguity as well as extra human intervention. Extensive experiments conducted on all 9 interactive segmentation datasets not only demonstrate the state-of-the-art segmentation performance of PiClick, but also reduces human interventions with multiple proposal generation and target reasoning. To promote direct usage and future endeavors, we release the source code of PiClick together with a plug-and-play annotation tool at https://github.com/cilinyan/PiClick.

SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been devoted to incorporating the benefits of pre-training. However, how to adaptively exploit the pre-trained knowledge for each incremental task while maintaining its generalizability remains an open question. In this work, we present an extensive analysis for continual learning on a pre-trained model (CLPM), and attribute the key challenge to a progressive overfitting problem. Observing that selectively reducing the learning rate can almost resolve this issue in the representation layer, we propose a simple but extremely effective approach named Slow Learner with Classifier Alignment (SLCA), which further improves the classification layer by modeling the class-wise distributions and aligning the classification layers in a post-hoc fashion. Across a variety of scenarios, our proposal provides substantial improvements for CLPM (e.g., up to 49.76%, 50.05%, 44.69% and 40.16% on Split CIFAR-100, Split ImageNet-R, Split CUB-200 and Split Cars-196, respectively), and thus outperforms state-of-the-art approaches by a large margin. Based on such a strong baseline, critical factors and promising directions are analyzed in-depth to facilitate subsequent research.

Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning

Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a meta-model which may fast adapt to novel classes with only a few exemplars and meanwhile remain robust to adversarial attacks. The conventional solution for robust MAML is to introduce robustness-promoting regularization during meta-training stage. With such a regularization, previous robust MAML methods simply follow the typical MAML practice that the number of training shots should match with the number of test shots to achieve an optimal adaptation performance. However, although the robustness can be largely improved, previous methods sacrifice clean accuracy a lot. In this paper, we observe that introducing robustness-promoting regularization into MAML reduces the intrinsic dimension of clean sample features, which results in a lower capacity of clean representations. This may explain why the clean accuracy of previous robust MAML methods drops severely. Based on this observation, we propose a simple strategy, i.e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robustness-promoting regularization. Though simple, our method remarkably improves the clean accuracy of MAML without much loss of robustness, producing a robust yet accurate model. Extensive experiments demonstrate that our method outperforms prior arts in achieving a better trade-off between accuracy and robustness. Besides, we observe that our method is less sensitive to the number of fine-tuning steps during meta-training, which allows for a reduced number of fine-tuning steps to improve training efficiency.