Questions you might face when interviewing for Computer Vision Engineer positions. Click to reveal answers, grouped by difficulty.
Transfer learning involves taking a model pre-trained on a large dataset and fine-tuning it on a smaller, task-specific dataset. It reduces training time and data requirements dramatically. Models like BERT and ResNet are commonly used as pre-trained bases for NLP and computer vision tasks.
Subclass torch.utils.data.Dataset, implement __len__ and __getitem__ methods. In __getitem__, load the image, apply transforms (resize, normalise, augment), and return the tensor and label. Wrap it in a DataLoader with batch_size, shuffle=True for training, num_workers for parallel loading, and pin_memory=True for GPU transfer speed.
In CNNs, convolution slides a learnable kernel (filter) across the input, computing element-wise multiplication and summing at each position. Technically it is cross-correlation (no kernel flip). For a 2D input, output[i,j] = sum(input[i+m, j+n] * kernel[m,n]). This operation extracts local features like edges, textures, and patterns while sharing parameters across spatial positions.
Edge deployment runs AI models on devices near the data source (phones, IoT devices, local servers) rather than in the cloud. It is appropriate when low latency is critical, network connectivity is unreliable (rural India), data privacy prevents cloud transmission, or cloud costs are prohibitive at scale. Requires model compression (quantisation, pruning) for device constraints.
Generative Adversarial Networks consist of two networks: a generator that creates synthetic data and a discriminator that distinguishes real from fake data. They are trained adversarially, with the generator improving at fooling the discriminator and the discriminator improving at detecting fakes. This process produces increasingly realistic synthetic data.
Use transfer learning with a pre-trained CNN like EfficientNet fine-tuned on labelled crop disease images. The model should handle diverse Indian crops and work offline on low-end devices via model quantisation. Include data augmentation for varying lighting and camera quality. Deploy as a lightweight mobile app with results in local languages.
For tables, extract and store them as structured text or markdown. For images, generate text descriptions using vision models and index those descriptions. For charts, extract underlying data points. Use multi-modal embedding models that can embed both text and images into the same space. Store modality metadata for filtering and presentation.
Collect Indian documents (Aadhaar, PAN cards, invoices in multiple scripts) with annotated fields. Use a pre-trained VLM like LLaVA or PaLI as the base. Create instruction data for OCR, field extraction, and document classification. Handle multiple Indian scripts (Devanagari, Tamil, Bengali, etc.). Fine-tune with LoRA on vision and language components. Evaluate on diverse document formats and quality levels.
