Exploring Better Text Image Translation with Multimodal Codebook

Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propose a TIT model with a multimodal codebook, which is able to associate the image with relevant texts, providing useful supplementary information for translation. Moreover, we present a multi-stage training framework involving text machine translation, image-text alignment, and TIT tasks, which fully exploits additional bilingual texts, OCR dataset and our OCRMT30K dataset to train our model. Extensive experiments and in-depth analyses strongly demonstrate the effectiveness of our proposed model and training framework.

Conditional Generation from Unconditional Diffusion Models using Denoiser Representations

Denoising diffusion models have gained popularity as a generative modeling technique for producing high-quality and diverse images. Applying these models to downstream tasks requires conditioning, which can take the form of text, class labels, or other forms of guidance. However, providing conditioning information to these models can be challenging, particularly when annotations are scarce or imprecise. In this paper, we propose adapting pre-trained unconditional diffusion models to new conditions using the learned internal representations of the denoiser network. We demonstrate the effectiveness of our approach on various conditional generation tasks, including attribute-conditioned generation and mask-conditioned generation. Additionally, we show that augmenting the Tiny ImageNet training set with synthetic images generated by our approach improves the classification accuracy of ResNet baselines by up to 8%. Our approach provides a powerful and flexible way to adapt diffusion models to new conditions and generate high-quality augmented data for various conditional generation tasks.

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings

Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, deep learning pipelines are notoriously data-hungry, while generating reference calculations is computationally demanding. To overcome this difficulty, we propose a transfer learning algorithm that leverages the ability of graph neural networks (GNNs) in describing chemical environments, together with kernel mean embeddings. We extract a feature map from GNNs pre-trained on the OC20 dataset and use it to learn the potential energy surface from system-specific datasets of catalytic processes. Our method is further enhanced by a flexible kernel function that incorporates chemical species information, resulting in improved performance and interpretability. We test our approach on a series of realistic datasets of increasing complexity, showing excellent generalization and transferability performance, and improving on methods that rely on GNNs or ridge regression alone, as well as similar fine-tuning approaches. We make the code available to the community at https://github.com/IsakFalk/atomistic_transfer_mekrr.

Cross-Attention is Not Enough: Incongruity-Aware Multimodal Sentiment Analysis and Emotion Recognition

Fusing multiple modalities for affective computing tasks has proven effective for performance improvement. However, how multimodal fusion works is not well understood, and its use in the real world usually results in large model sizes. In this work, on sentiment and emotion analysis, we first analyze how the salient affective information in one modality can be affected by the other in crossmodal attention. We find that inter-modal incongruity exists at the latent level due to crossmodal attention. Based on this finding, we propose a lightweight model via Hierarchical Crossmodal Transformer with Modality Gating (HCT-MG), which determines a primary modality according to its contribution to the target task and then hierarchically incorporates auxiliary modalities to alleviate inter-modal incongruity and reduce information redundancy. The experimental evaluation on three benchmark datasets: CMU-MOSI, CMU-MOSEI, and IEMOCAP verifies the efficacy of our approach, showing that it: 1) outperforms major prior work by achieving competitive results and can successfully recognize hard samples; 2) mitigates the inter-modal incongruity at the latent level when modalities have mismatched affective tendencies; 3) reduces model size to less than 1M parameters while outperforming existing models of similar sizes.

EDIS: Entity-Driven Image Search over Multimodal Web Content

Making image retrieval methods practical for real-world search applications requires significant progress in dataset scales, entity comprehension, and multimodal information fusion. In this work, we introduce \textbf{E}ntity-\textbf{D}riven \textbf{I}mage \textbf{S}earch (EDIS), a challenging dataset for cross-modal image search in the news domain. EDIS consists of 1 million web images from actual search engine results and curated datasets, with each image paired with a textual description. Unlike datasets that assume a small set of single-modality candidates, EDIS reflects real-world web image search scenarios by including a million multimodal image-text pairs as candidates. EDIS encourages the development of retrieval models that simultaneously address cross-modal information fusion and matching. To achieve accurate ranking results, a model must: 1) understand named entities and events from text queries, 2) ground entities onto images or text descriptions, and 3) effectively fuse textual and visual representations. Our experimental results show that EDIS challenges state-of-the-art methods with dense entities and a large-scale candidate set. The ablation study also proves that fusing textual features with visual features is critical in improving retrieval results.

Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion

Nowadays, recognition-synthesis-based methods have been quite popular with voice conversion (VC). By introducing linguistics features with good disentangling characters extracted from an automatic speech recognition (ASR) model, the VC performance achieved considerable breakthroughs. Recently, self-supervised learning (SSL) methods trained with a large-scale unannotated speech corpus have been applied to downstream tasks focusing on the content information, which is suitable for VC tasks. However, a huge amount of speaker information in SSL representations degrades timbre similarity and the quality of converted speech significantly. To address this problem, we proposed a high-similarity any-to-one voice conversion method with the input of SSL representations. We incorporated adversarial training mechanisms in the synthesis module using external unannotated corpora. Two auxiliary discriminators were trained to distinguish whether a sequence of mel-spectrograms has been converted by the acoustic model and whether a sequence of content embeddings contains speaker information from external corpora. Experimental results show that our proposed method achieves comparable similarity and higher naturalness than the supervised method, which needs a huge amount of annotated corpora for training and is applicable to improve similarity for VC methods with other SSL representations as input.

Block-local learning with probabilistic latent representations

The ubiquitous backpropagation algorithm requires sequential updates across blocks of a network, introducing a locking problem. Moreover, backpropagation relies on the transpose of weight matrices to calculate updates, introducing a weight transport problem across blocks. Both these issues prevent efficient parallelisation and horizontal scaling of models across devices. We propose a new method that introduces a twin network that propagates information backwards from the targets to the input to provide auxiliary local losses. Forward and backward propagation can work in parallel and with different sets of weights, addressing the problems of weight transport and locking. Our approach derives from a statistical interpretation of end-to-end training which treats activations of network layers as parameters of probability distributions. The resulting learning framework uses these parameters locally to assess the matching between forward and backward information. Error backpropagation is then performed locally within each block, leading to `block-local' learning. Several previously proposed alternatives to error backpropagation emerge as special cases of our model. We present results on various tasks and architectures, including transformers, demonstrating state-of-the-art performance using block-local learning. These results provide a new principled framework to train very large networks in a distributed setting and can also be applied in neuromorphic systems.

A Causal View of Entity Bias in (Large) Language Models

Entity bias widely affects pretrained (large) language models, causing them to excessively rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired methods have shown great potential to mitigate entity bias, it is hard to precisely estimate the parameters of underlying causal models in practice. The rise of black-box LLMs also makes the situation even worse, because of their inaccessible parameters and uncalibrated logits. To address these problems, we propose a specific structured causal model (SCM) whose parameters are comparatively easier to estimate. Building upon this SCM, we propose causal intervention techniques to mitigate entity bias for both white-box and black-box settings. The proposed causal intervention perturbs the original entity with neighboring entities. This intervention reduces specific biasing information pertaining to the original entity while still preserving sufficient common predictive information from similar entities. When evaluated on the relation extraction task, our training-time intervention significantly improves the F1 score of RoBERTa by 5.7 points on EntRED, in which spurious shortcuts between entities and labels are removed. Meanwhile, our in-context intervention effectively reduces the knowledge conflicts between parametric knowledge and contextual knowledge in GPT-3.5 and improves the F1 score by 9.14 points on a challenging test set derived from Re-TACRED.

Optimization-Based Improvement of Face Image Quality Assessment Techniques

Contemporary face recognition (FR) models achieve near-ideal recognition performance in constrained settings, yet do not fully translate the performance to unconstrained (realworld) scenarios. To help improve the performance and stability of FR systems in such unconstrained settings, face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process. While existing FIQA techniques are able to efficiently capture the differences between high and low quality images, they typically cannot fully distinguish between images of similar quality, leading to lower performance in many scenarios. To address this issue, we present in this paper a supervised quality-label optimization approach, aimed at improving the performance of existing FIQA techniques. The developed optimization procedure infuses additional information (computed with a selected FR model) into the initial quality scores generated with a given FIQA technique to produce better estimates of the "actual" image quality. We evaluate the proposed approach in comprehensive experiments with six state-of-the-art FIQA approaches (CR-FIQA, FaceQAN, SER-FIQ, PCNet, MagFace, SDD-FIQA) on five commonly used benchmarks (LFW, CFPFP, CPLFW, CALFW, XQLFW) using three targeted FR models (ArcFace, ElasticFace, CurricularFace) with highly encouraging results.

LLMDet: A Large Language Models Detection Tool

With the advancement of generative language models, the generated text has come remarkably close to high-quality human-authored text in terms of fluency and diversity. This calls for a highly practical detection tool that can identify the source of text, preferably pinpointing the language model it originates from. However, existing detection tools typically require access to language models and can only differentiate between machine-generated and human-authored text, failing to meet the requirements of rapid detection and text tracing. Therefore, in this paper, we propose an efficient, secure, and scalable detection tool called LLMDet, which calculates the proxy perplexity of text by utilizing the prior information of the model's next-token probabilities, obtained through pre-training. Subsequently, we use the self-watermarking information of the model, as measured by proxy perplexity, to detect the source of the text. We found that our method demonstrates impressive detection performance while ensuring speed and security, particularly achieving a recognition accuracy of 97.97\% for human-authored text. Furthermore, our detection tool also shows promising results in identifying the large language model (e.g., GPT-2, OPT, LLaMA, Vicuna...) responsible for the text. We release the code and processed data at \url{https://github.com/TrustedLLM/LLMDet}.