Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption conditioned on an input image and related captions retrieved from a datastore. Our model is lightweight and fast to train, as the only learned parameters are in newly introduced cross-attention layers between a pre-trained CLIP encoder and GPT-2 decoder. SmallCap can transfer to new domains without additional finetuning and can exploit large-scale data in a training-free fashion since the contents of the datastore can be readily replaced. Our experiments show that SmallCap, trained only on COCO, has competitive performance on this benchmark, and also transfers to other domains without retraining, solely through retrieval from target-domain data. Further improvement is achieved through the training-free exploitation of diverse human-labeled and web data, which proves to be effective for a range of domains, including the nocaps benchmark, designed to test generalization to unseen visual concepts.
相關內容
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions. Previous methods fine-tune pre-trained models with various side information and learning strategies to learn a compact feature space that is shared between the sketch and photo domains and bridges seen and unseen classes. However, these efforts are inadequate in adapting domains and transferring knowledge from seen to unseen classes. In this paper, we present an effective ``Adapt and Align'' approach to address the key challenges. Specifically, we insert simple and lightweight domain adapters to learn new abstract concepts of the sketch domain and improve cross-domain representation capabilities. Inspired by recent advances in image-text foundation models (e.g., CLIP) on zero-shot scenarios, we explicitly align the learned image embedding with a more semantic text embedding to achieve the desired knowledge transfer from seen to unseen classes. Extensive experiments on three benchmark datasets and two popular backbones demonstrate the superiority of our method in terms of retrieval accuracy and flexibility.
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired data to accomplish this task while generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and learn correspondences in appearance instead of semantic content. Starting from the assumption that a high quality generated image should be segmented back to its semantic layout, we propose a new Unsupervised paradigm for SIS (USIS) that makes use of a self-supervised segmentation loss and whole image wavelet based discrimination. Furthermore, in order to match the high-frequency distribution of real images, a novel generator architecture in the wavelet domain is proposed. We test our methodology on 3 challenging datasets and demonstrate its ability to bridge the performance gap between paired and unpaired models.
Medical image segmentation is a critical step in computer-aided diagnosis, and convolutional neural networks are popular segmentation networks nowadays. However, the inherent local operation characteristics make it difficult to focus on the global contextual information of lesions with different positions, shapes, and sizes. Semi-supervised learning can be used to learn from both labeled and unlabeled samples, alleviating the burden of manual labeling. However, obtaining a large number of unlabeled images in medical scenarios remains challenging. To address these issues, we propose a Multi-level Global Context Cross-consistency (MGCC) framework that uses images generated by a Latent Diffusion Model (LDM) as unlabeled images for semi-supervised learning. The framework involves of two stages. In the first stage, a LDM is used to generate synthetic medical images, which reduces the workload of data annotation and addresses privacy concerns associated with collecting medical data. In the second stage, varying levels of global context noise perturbation are added to the input of the auxiliary decoder, and output consistency is maintained between decoders to improve the representation ability. Experiments conducted on open-source breast ultrasound and private thyroid ultrasound datasets demonstrate the effectiveness of our framework in bridging the probability distribution and the semantic representation of the medical image. Our approach enables the effective transfer of probability distribution knowledge to the segmentation network, resulting in improved segmentation accuracy. The code is available at //github.com/FengheTan9/Multi-Level Global-Context-Cross-Consistency.
Contrastive self-supervised learning is widely employed in visual recognition for geographic image data (remote or proximal sensing), but because of landscape heterogeneity, models can show disparate performance across spatial units. In this work, we consider fairness risks in such contrastive pre-training; we show learnt representations present large performance gaps across selected sensitive groups: urban and rural areas for satellite images and city GDP level for street view images on downstream semantic segmentation. We propose fair dense representations with contrastive learning (FairDCL) to address the issue, a multi-level latent space de-biasing objective, using a novel dense sensitive attribute encoding technique to constrain spurious local information disparately distributes across groups. The method achieves improved downstream task fairness and outperforms state-of-the-art methods for the absence of a fairness-accuracy trade-off. Image embedding evaluation and ablation studies further demonstrate effectiveness of FairDCL. As fairness in geographic imagery is a nascent topic without existing state-of-the-art data or results, our work motivates researchers to consider fairness metrics in such applications, especially reinforced by our results showing no accuracy degradation. Our code is available at: //anonymous.4open.science/r/FairDCL-1283
In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages. We demonstrate that applying state-of-the-art approaches developed for cross-lingual information retrieval to MLIR tasks leads to sub-optimal performance. This is due to the heterogeneous and imbalanced nature of multilingual collections -- some languages are better represented in the collection and some benefit from large-scale training data. To address this issue, we present KD-SPD, a novel soft prompt decoding approach for MLIR that implicitly "translates" the representation of documents in different languages into the same embedding space. To address the challenges of data scarcity and imbalance, we introduce a knowledge distillation strategy. The teacher model is trained on rich English retrieval data, and by leveraging bi-text data, our distillation framework transfers its retrieval knowledge to the multilingual document encoder. Therefore, our approach does not require any multilingual retrieval training data. Extensive experiments on three MLIR datasets with a total of 15 languages demonstrate that KD-SPD significantly outperforms competitive baselines in all cases. We conduct extensive analyses to show that our method has less language bias and better zero-shot transfer ability towards new languages.
In recent years a vast amount of visual content has been generated and shared from various fields, such as social media platforms, medical images, and robotics. This abundance of content creation and sharing has introduced new challenges. In particular, searching databases for similar content, i.e. content based image retrieval (CBIR), is a long-established research area, and more efficient and accurate methods are needed for real time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of intelligent search. In this survey we organize and review recent CBIR works that are developed based on deep learning algorithms and techniques, including insights and techniques from recent papers. We identify and present the commonly-used databases, benchmarks, and evaluation methods used in the field. We collect common challenges and propose promising future directions. More specifically, we focus on image retrieval with deep learning and organize the state of the art methods according to the types of deep network structure, deep features, feature enhancement methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, aiming to promote a global view of the field of category-based CBIR.
Deep learning-based semi-supervised learning (SSL) algorithms have led to promising results in medical images segmentation and can alleviate doctors' expensive annotations by leveraging unlabeled data. However, most of the existing SSL algorithms in literature tend to regularize the model training by perturbing networks and/or data. Observing that multi/dual-task learning attends to various levels of information which have inherent prediction perturbation, we ask the question in this work: can we explicitly build task-level regularization rather than implicitly constructing networks- and/or data-level perturbation-and-transformation for SSL? To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. Concretely, we use a dual-task deep network that jointly predicts a pixel-wise segmentation map and a geometry-aware level set representation of the target. The level set representation is converted to an approximated segmentation map through a differentiable task transform layer. Simultaneously, we introduce a dual-task consistency regularization between the level set-derived segmentation maps and directly predicted segmentation maps for both labeled and unlabeled data. Extensive experiments on two public datasets show that our method can largely improve the performance by incorporating the unlabeled data. Meanwhile, our framework outperforms the state-of-the-art semi-supervised medical image segmentation methods. Code is available at: //github.com/Luoxd1996/DTC
This paper discusses and demonstrates the outcomes from our experimentation on Image Captioning. Image captioning is a much more involved task than image recognition or classification, because of the additional challenge of recognizing the interdependence between the objects/concepts in the image and the creation of a succinct sentential narration. Experiments on several labeled datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. As a toy application, we apply image captioning to create video captions, and we advance a few hypotheses on the challenges we encountered.
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevents direct influence of the language description to the event proposal, which is important for generating accurate descriptions. To address this problem, we propose an end-to-end transformer model for dense video captioning. The encoder encodes the video into appropriate representations. The proposal decoder decodes from the encoding with different anchors to form video event proposals. The captioning decoder employs a masking network to restrict its attention to the proposal event over the encoding feature. This masking network converts the event proposal to a differentiable mask, which ensures the consistency between the proposal and captioning during training. In addition, our model employs a self-attention mechanism, which enables the use of efficient non-recurrent structure during encoding and leads to performance improvements. We demonstrate the effectiveness of this end-to-end model on ActivityNet Captions and YouCookII datasets, where we achieved 10.12 and 6.58 METEOR score, respectively.
Automatic image captioning has recently approached human-level performance due to the latest advances in computer vision and natural language understanding. However, most of the current models can only generate plain factual descriptions about the content of a given image. However, for human beings, image caption writing is quite flexible and diverse, where additional language dimensions, such as emotion, humor and language styles, are often incorporated to produce diverse, emotional, or appealing captions. In particular, we are interested in generating sentiment-conveying image descriptions, which has received little attention. The main challenge is how to effectively inject sentiments into the generated captions without altering the semantic matching between the visual content and the generated descriptions. In this work, we propose two different models, which employ different schemes for injecting sentiments into image captions. Compared with the few existing approaches, the proposed models are much simpler and yet more effective. The experimental results show that our model outperform the state-of-the-art models in generating sentimental (i.e., sentiment-bearing) image captions. In addition, we can also easily manipulate the model by assigning different sentiments to the testing image to generate captions with the corresponding sentiments.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191